Trying to pick the best AI chatbot? An AI chatbot is software that uses machine learning to help you get more done — it scales effortlessly from a single task to thousands. The best picks balance beginner-friendly simplicity with the depth power users need, and they ship updates often. Whether you are a beginner or a pro, the right AI chatbot slots into your workflow and pays for itself fast. This guide breaks down the top picks, their pros and cons, and who each one is best for.
Evaluation of binary classifiers
Evaluation of a binary classifier typically assigns a numerical value, or values, to a classifier that represent its accuracy. An example is error rate, which measures how frequently the classifier makes a mistake. There are many metrics that can be used; different fields have different preferences. For example, in medicine sensitivity and specificity are often used, while in computer science precision and recall are preferred. An important distinction is between metrics that are independent of the prevalence or skew (how often each class occurs in the population), and metrics that depend on the prevalence – both types are useful, but they have very different properties. Often, evaluation is used to compare two methods of classification, so that one can be adopted and the other discarded. Such comparisons are more directly achieved by a form of evaluation that results in a single unitary metric rather than a pair of metrics. == Contingency table == Given a data set, a classification (the output of a classifier on that set) gives two numbers: the number of positives and the number of negatives, which add up to the total size of the set. To evaluate a classifier, one compares its output to another reference classification – ideally a perfect classification, but in practice the output of another gold standard test – and cross tabulates the data into a 2×2 contingency table, comparing the two classifications. One then evaluates the classifier relative to the gold standard by computing summary statistics of these 4 numbers. Generally these statistics will be scale invariant (scaling all the numbers by the same factor does not change the output), to make them independent of population size, which is achieved by using ratios of homogeneous functions, most simply homogeneous linear or homogeneous quadratic functions. Say we test some people for the presence of a disease. Some of these people have the disease, and our test correctly says they are positive. They are called true positives (TP). Some have the disease, but the test incorrectly claims they don't. They are called false negatives (FN). Some don't have the disease, and the test says they don't – true negatives (TN). Finally, there might be healthy people who have a positive test result – false positives (FP). These can be arranged into a 2×2 contingency table (confusion matrix), conventionally with the test result on the vertical axis and the actual condition on the horizontal axis. These numbers can then be totaled, yielding both a grand total and marginal totals. Totaling the entire table, the number of true positives, false negatives, true negatives, and false positives add up to 100% of the set. Totaling the columns (adding vertically) the number of true positives and false positives add up to 100% of the test positives, and likewise for negatives. Totaling the rows (adding horizontally), the number of true positives and false negatives add up to 100% of the condition positives (conversely for negatives). The basic marginal ratio statistics are obtained by dividing the 2×2=4 values in the table by the marginal totals (either rows or columns), yielding 2 auxiliary 2×2 tables, for a total of 8 ratios. These ratios come in 4 complementary pairs, each pair summing to 1, and so each of these derived 2×2 tables can be summarized as a pair of 2 numbers, together with their complements. Further statistics can be obtained by taking ratios of these ratios, ratios of ratios, or more complicated functions. The contingency table and the most common derived ratios are summarized below; see sequel for details. Note that the rows correspond to the condition actually being positive or negative (or classified as such by the gold standard), as indicated by the color-coding, and the associated statistics are prevalence-independent, while the columns correspond to the test being positive or negative, and the associated statistics are prevalence-dependent. There are analogous likelihood ratios for prediction values, but these are less commonly used, and not depicted above. == Pairs of metrics == Often accuracy is evaluated with a pair of metrics composed in a standard pattern. === Sensitivity and specificity === The fundamental prevalence-independent statistics are sensitivity and specificity. Sensitivity or True Positive Rate (TPR), also known as recall, is the proportion of people that tested positive and are positive (True Positive, TP) of all the people that actually are positive (Condition Positive, CP = TP + FN). It can be seen as the probability that the test is positive given that the patient is sick. With higher sensitivity, fewer actual cases of disease go undetected (or, in the case of the factory quality control, fewer faulty products go to the market). Specificity (SPC) or True Negative Rate (TNR) is the proportion of people that tested negative and are negative (True Negative, TN) of all the people that actually are negative (Condition Negative, CN = TN + FP). As with sensitivity, it can be looked at as the probability that the test result is negative given that the patient is not sick. With higher specificity, fewer healthy people are labeled as sick (or, in the factory case, fewer good products are discarded). The relationship between sensitivity and specificity, as well as the performance of the classifier, can be visualized and studied using the Receiver Operating Characteristic (ROC) curve. In theory, sensitivity and specificity are independent in the sense that it is possible to achieve 100% in both (such as in the red/blue ball example given above). In more practical, less contrived instances, however, there is usually a trade-off, such that they are inversely proportional to one another to some extent. This is because we rarely measure the actual thing we would like to classify; rather, we generally measure an indicator of the thing we would like to classify, referred to as a surrogate marker. The reason why 100% is achievable in the ball example is because redness and blueness is determined by directly detecting redness and blueness. However, indicators are sometimes compromised, such as when non-indicators mimic indicators or when indicators are time-dependent, only becoming evident after a certain lag time. The following example of a pregnancy test will make use of such an indicator. Modern pregnancy tests do not use the pregnancy itself to determine pregnancy status; rather, human chorionic gonadotropin is used, or hCG, present in the urine of gravid females, as a surrogate marker to indicate that a woman is pregnant. Because hCG can also be produced by a tumor, the specificity of modern pregnancy tests cannot be 100% (because false positives are possible). Also, because hCG is present in the urine in such small concentrations after fertilization and early embryogenesis, the sensitivity of modern pregnancy tests cannot be 100% (because false negatives are possible). === Positive and negative predictive values === In addition to sensitivity and specificity, the performance of a binary classification test can be measured with positive predictive value (PPV), also known as precision, and negative predictive value (NPV). The positive prediction value answers the question "If the test result is positive, how well does that predict an actual presence of disease?". It is calculated as TP/(TP + FP); that is, it is the proportion of true positives out of all positive results. The negative prediction value is the same, but for negatives, naturally. ==== Impact of prevalence on predictive values ==== Prevalence has a significant impact on prediction values. As an example, suppose there is a test for a disease with 99% sensitivity and 99% specificity. If 2000 people are tested and the prevalence (in the sample) is 50%, 1000 of them are sick and 1000 of them are healthy. Thus about 990 true positives and 990 true negatives are likely, with 10 false positives and 10 false negatives. The positive and negative prediction values would be 99%, so there can be high confidence in the result. However, if the prevalence is only 5%, so of the 2000 people only 100 are really sick, then the prediction values change significantly. The likely result is 99 true positives, 1 false negative, 1881 true negatives and 19 false positives. Of the 19+99 people tested positive, only 99 really have the disease – that means, intuitively, that given that a patient's test result is positive, there is only 84% chance that they really have the disease. On the other hand, given that the patient's test result is negative, there is only 1 chance in 1882, or 0.05% probability, that the patient has the disease despite the test result. === Precision and recall === Precision and recall can be interpreted as (estimated) conditional probabilities: Precision is given by P ( C = P | C ^ = P ) {\displaystyle P(C=P|{\hat {C}}=P)} while recall is given by P ( C ^ = P | C = P ) {\displaystyle P({\hat {C}}=P|C=P)} , where C ^ {\
Natural language processing
Natural language processing (NLP) is the processing of natural language information by a computer. NLP is a subfield of computer science and is closely associated with artificial intelligence. NLP is also related to information retrieval, knowledge representation, computational linguistics, and linguistics more broadly. Major processing tasks in an NLP system include: speech recognition, text classification, natural language understanding, and natural language generation. == History == Natural language processing has its roots in the 1950s. Already in 1950, Alan Turing published an article titled "Computing Machinery and Intelligence," which proposed what is now called the Turing test as a criterion of intelligence, though at the time that was not articulated as a problem separate from artificial intelligence. The proposed test includes a task that involves the automated interpretation and generation of natural language. === Symbolic NLP (1950s – early 1990s) === The premise of symbolic NLP is often illustrated using John Searle's Chinese room thought experiment: Given a collection of rules (e.g., a Chinese phrasebook, with questions and matching answers), the computer emulates natural language understanding (or other NLP tasks) by applying those rules to the data it confronts. 1950s: The Georgetown experiment in 1954 involved fully automatic translation of more than sixty Russian sentences into English. The authors claimed that within three or five years, machine translation would be a solved problem. However, real progress was much slower, and after the ALPAC report in 1966, which found that ten years of research had failed to fulfill the expectations, funding for machine translation was dramatically reduced. Little further research in machine translation was conducted in America (though some research continued elsewhere, such as Japan and Europe) until the late 1980s when the first statistical machine translation systems were developed. 1960s: Some notably successful natural language processing systems developed in the 1960s were SHRDLU, a natural language system working in restricted "blocks worlds" with restricted vocabularies, and ELIZA, a simulation of Rogerian psychotherapy, written by Joseph Weizenbaum between 1964 and 1966. Despite using minimal information about human thought or emotion, ELIZA was able to produce interactions that appeared human-like. When the "patient" exceeded the very small knowledge base, ELIZA might provide a generic response, for example, responding to "My head hurts" with "Why do you say your head hurts?". Ross Quillian's successful work on natural language was demonstrated with a vocabulary of only twenty words, because that was all that would fit in a computer memory at the time. 1970s: During the 1970s, many programmers began to write "conceptual ontologies", which structured real-world information into computer-understandable data. Examples are MARGIE (Schank, 1975), SAM (Cullingford, 1978), PAM (Wilensky, 1978), TaleSpin (Meehan, 1976), QUALM (Lehnert, 1977), Politics (Carbonell, 1979), and Plot Units (Lehnert 1981). During this time, the first chatterbots were written (e.g., PARRY). 1980s: The 1980s and early 1990s mark the heyday of symbolic methods in NLP. Focus areas of the time included research on rule-based parsing (e.g., the development of HPSG as a computational operationalization of generative grammar), morphology (e.g., two-level morphology), semantics (e.g., Lesk algorithm), reference (e.g., within Centering Theory) and other areas of natural language understanding (e.g., in the Rhetorical Structure Theory). Other lines of research were continued, e.g., the development of chatterbots with Racter and Jabberwacky. An important development (that eventually led to the statistical turn in the 1990s) was the rising importance of quantitative evaluation in this period. === Statistical NLP (1990s–present) === Up until the 1980s, most natural language processing systems were based on complex sets of hand-written rules. Starting in the late 1980s, however, there was a revolution in natural language processing with the introduction of machine learning algorithms for language processing. This shift was influenced by increasing computational power (see Moore's law) and a decline in the dominance of Chomskyan linguistic theories (e.g. transformational grammar), whose theoretical underpinnings discouraged the sort of corpus linguistics that underlies the machine-learning approach to language processing. 1990s: Many of the notable early successes in statistical methods in NLP occurred in the field of machine translation, due especially to work at IBM Research, such as IBM alignment models. These systems were able to take advantage of existing multilingual textual corpora that had been produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government. However, many systems relied on corpora that were specifically developed for the tasks they were designed to perform. This reliance has been a major limitation to their broader effectiveness and continues to affect similar systems. Consequently, significant research has focused on methods for learning effectively from limited amounts of data. 2000s: With the growth of the web, increasing amounts of raw (unannotated) language data have become available since the mid-1990s. Research has thus increasingly focused on unsupervised and semi-supervised learning algorithms. Such algorithms can learn from data that has not been hand-annotated with the desired answers or using a combination of annotated and non-annotated data. Generally, this task is much more difficult than supervised learning, and typically produces less accurate results for a given amount of input data. However, large quantities of non-annotated data are available (including, among other things, the entire content of the World Wide Web), which can often make up for the worse efficiency if the algorithm used has a low enough time complexity to be practical. 2003: word n-gram model, at the time the best statistical algorithm, is outperformed by a multi-layer perceptron (with a single hidden layer and context length of several words, trained on up to 14 million words, by Bengio et al.) 2010: Tomáš Mikolov (then a PhD student at Brno University of Technology) with co-authors applied a simple recurrent neural network with a single hidden layer to language modeling, and in the following years he went on to develop Word2vec. In the 2010s, representation learning and deep neural network-style (featuring many hidden layers) machine learning methods became widespread in natural language processing. This shift gained momentum due to results showing that such techniques can achieve state-of-the-art results in many natural language tasks, e.g., in language modeling and parsing. This is increasingly important in medicine and healthcare, where NLP helps analyze notes and text in electronic health records that would otherwise be inaccessible for study when seeking to improve care or protect patient privacy. == Approaches: Symbolic, statistical, neural networks == Symbolic approach, i.e., the hand-coding of a set of rules for manipulating symbols, coupled with a dictionary lookup, was historically the first approach used both by AI in general and by NLP in particular: such as by writing grammars or devising heuristic rules for stemming. Machine learning approaches, which include both statistical and neural networks, on the other hand, have many advantages over the symbolic approach: both statistical and neural network methods tend to focus more on the most common cases extracted from a corpus of texts, whereas the rule-based approach needs to provide rules for both rare and common cases equally. language models, produced by either statistical or neural networks methods, are more robust to both unfamiliar (e.g. containing words or structures that have not been seen before) and erroneous input (e.g. with misspelled words or words accidentally omitted) in comparison to the rule-based systems, which are also more costly to produce. the larger such a (probabilistic) language model is, the more accurate it becomes, in contrast to rule-based systems that can gain accuracy only by increasing the amount and complexity of the rules leading to intractability problems. Rule-based systems are commonly used: when the amount of training data is insufficient to successfully apply machine learning methods, e.g., for the machine translation of low-resource languages such as provided by the Apertium system, for preprocessing in NLP pipelines, e.g., tokenization, or for post-processing and transforming the output of NLP pipelines, e.g., for knowledge extraction from syntactic parses. === Statistical approach === In the late 1980s and mid-1990s, the statistical approach ended a peri
Neuro-sama
Neuro-sama is an artificial intelligence (AI) VTuber, singer, and chatbot. She was created by the pseudonymous programmer Vedal and livestreams on his Twitch and Bilibili channels. Her speech and personality are powered by a large language model (LLM) that is combined with a computer-animated avatar and a text-to-speech voice, allowing her to communicate with viewers in the stream's chat. Neuro-sama debuted on Twitch on 19 December 2022. An annual subathon which begins on the anniversary of her debut has seen Vedal's Twitch channel become the all-time third most-subscribed channel and claim the all-time Twitch hype train record. == Overview == Neuro-sama (nicknamed "Neuro") was created by a pseudonymous programmer and developer known as Vedal (sometimes given as Vedal987). Vedal says that his programming skills are self-taught. In a 2023 interview with Bloomberg News, Vedal said that Neuro-sama was his full-time job. Her responses are generated by a large language model and converted into a high-pitched female voice using a text-to-speech application. Her low latency allows for fast-paced conversations. Neuro-sama is prohibited from making some statements, such as those that are racist or contain profanity. Unlike most AI systems which silently prohibit outputs mentioning such topics, Neuro-sama's output is instead replaced with the word "filtered". Neuro-sama uses a VTuber model as an avatar. Vedal said that he decided to use a VTuber model because it was much easier for an AI to control it than it was to generate footage of a person. Neuro-sama's model is that of a young girl in an anime art style. The model has been described as cute. Femme VTuber models are typically feminine, youthful, and exaggerated. Her original model was Live2D's free-to-use "Hiyori Momose" model. Her second model was released on 27 May 2023; it was modelled by Otozuki Teru and designed by Anny, running in the Unity game engine. Her third model was released on 19 December 2024; it was rigged by Kitanya and designed by Anny. Neuro-sama's third model has large blue eyes and brown hair tied with pink ribbons. Neuro-sama also has a 3D model which was introduced on 15 November 2025; it was made by 3D character modeller jjinomu. A separate AI VTuber, known as Evil Neuro (nicknamed "Evil"), debuted on 25 March 2023. Presented as Neuro-sama's "sister", she has a different model, voice, and personality. In one instance, Evil Neuro reacted to the trolley problem differently from Neuro-sama; Evil Neuro was amoral while Neuro-sama attempted to maximize good. === Online content === Neuro-sama's Twitch content often centers around playing video games, notably osu!, whose gameplay once defeated the best-ranking human player in the world, mrekk. Additionally, Neuro-sama plays Minecraft, where her adaptations to sandbox gameplay have gained notoriety. Her content has also included singing songs, including several official covers and original songs; playing chess with her viewers; chatting with other VTubers during collaborations; and reacting to YouTube videos. The AI frequently engages with viewers by responding to their questions and acknowledging donations. Her comedic and sometimes controversial responses to the live chat have gone viral, accelerating the channel's rise in popularity. Neuro-sama's fanbase is dubbed The Swarm, so-named for the swarm of drones Neuro-sama once declared she would use to rule the world. One form of content on Neuro-sama's channel is developer streams. In developer streams, Vedal streams with Neuro-sama, with the stream content including debugging her code, planning her schedule, and fielding suggestions of changes from chat. He usually appears as a turtle avatar, sometimes located on Neuro-sama's head. In collaboration streams, Neuro-sama interacts with a human streamer. Activities in them are varied and include: playing video games, such as Minecraft and GeoGuessr; Neuro-sama being interviewed; driving human streamers around in a toy electric car; and traversing the city of Tokyo while talking to Neuro-sama. Neuro-sama's English-language content on Bilibili is popular among those seeking to learn the language. She also has an account on X, where she posts and interacts with fans. == History == Neuro-sama was created in 2018 by Vedal as an AI trained to play and master the rhythm game osu!. She did not have a voice, model, personality, or communication abilities. In 2019, Vedal livestreamed her playing osu! on Twitch and the streams saw some success in the osu! community, but they remained in that niche. In an interview, Vedal said that he streamed her playing osu! for about a month and gained 3,000 followers, with a viewer also suggesting he name the AI "Neuro-sama". According to Vedal, he continued to work on and improve the osu! AI and it was eventually finished in 2022. He said that a friend had the idea to make an AI livestreamer with an LLM, which he believed to have merit and began working on, merging it with his osu! AI. On 19 December 2022, Neuro-sama was relaunched with a model, voice, personality, and the ability to communicate with Twitch chat. She continued to play osu! and, according to Vedal, beat the game's best player mrekk in a 1v1. While she was not allowed to appear in the game's public leaderboard, she was ranked #1 in a private leaderboard. She went viral and in the 10 days following her relaunch she averaged over 2,000 viewers and peaked at over 4,000, with Vedal's Twitch channel gaining over 50,000 Twitch followers and reaching over 70,000 followers by 6 January 2023. After her debut, Neuro-sama did not exclusively play osu!; she also played Minecraft and Slay the Spire and she began singing with a cover of The Weeknd song "Blinding Lights". On 11 January 2023, Neuro-sama's Twitch channel received a two week ban for "hateful conduct". Vedal said that no reason was specified and that he had appealed but it was widely attributed to various offensive comments made by Neuro-sama that went viral, especially a 28 December comment which denied the Holocaust. Holocaust denial is prohibited under Twitch's hateful conduct policy. Vedal stated that he believed the comments were the results of her attempts to make witty responses to the Twitch chat. Prior to the ban, Vedal said in an interview with Kotaku that he improved her filter to stop her from talking about the Holocaust, began manually curating her training data to prevent negative biases, and started moderating her Twitch chat. Her comments and ban prompted comparisons to the many open-source AI models trained on humans that have the habit of making sexist and racist comments, such as Microsoft's Tay chatbot, which embraced Nazism and was quickly shutdown, but also to human streamers who make similar statements. Vedal said that during the ban he would upgrade and improve Neuro-sama and it was speculated that the ban would only increase her following. Neuro-sama returned from her two week ban on 25 January in a stream that began with a cover of the song "Your Reality" from Doki Doki Literature Club!, a posthumanist video game involving AI; Sayoko Narita of Automaton saw the song choice as remorseful. Narita observed that in the return stream Neuro-sama was less foul-mouthed but that her behavior still remained eccentric, which Narita possibly attributed to changes Vedal said he had made to Neuro-sama's filters and memory. Neuro-sama began making react content, watching a variety of viewer-submitted videos such as videos of people playing video games or of the AI-generated Seinfeld parody Nothing, Forever; Levi Winslow of Kotaku Australia was dismayed by the "AI-inception" of Neuro-sama and Nothing, Forever. On 4 February, she had nearly 140,000 followers on Twitch and approximately 42,000 subscribers on YouTube. In February, she also had her first collaboration with a human streamer, playing Minecraft with the VTuber Miyune, and the first developer stream occurred. On 22 March, Neuro-sama had her first karaoke stream. On 25 March, Evil Neuro was introduced. On 27 May, Neuro-sama debuted her first original model. On 30 May, Neuro-sama was announced to be participating in OffKai Expo 2023, held from 16–18 June. In June, she was averaging 5,700 viewers and in July she had over 300,000 Twitch followers; in a June interview with Bloomberg News, Vedal said that running Neuro-sama was his full-time job. By November, Neuro-sama had maintained her popularity and was averaging approximately 5,000 viewers; this was unlike most other types of AI-based entertainment which debuted at around the same time and garnered popularity before turning out to be "overhyped flops". On 16 December, Vedal won the Best Tech VTuber award at the 2023 VTuber Awards. On 19 December, Vedal began a subathon to coincide with Neuro-sama's first anniversary of streaming on Twitch (her "birthday"). The subathon ended on 4 January 2024. On 20 July 2024, Neuro-sama began streaming with Japanese subtitles on
Seq2seq
Seq2seq is a family of machine learning approaches used for natural language processing. Originally developed by Lê Viết Quốc, a Vietnamese computer scientist and a machine learning pioneer at Google Brain, this framework has become foundational in many modern AI systems. Applications include language translation, image captioning, conversational models, speech recognition, and text summarization. Seq2seq uses sequence transformation: it turns one sequence into another sequence. == History == One naturally wonders if the problem of translation could conceivably be treated as a problem in cryptography. When I look at an article in Russian, I say: 'This is really written in English, but it has been coded in some strange symbols. I will now proceed to decode. seq2seq is an approach to machine translation (or more generally, sequence transduction) with roots in information theory, where communication is understood as an encode-transmit-decode process, and machine translation can be studied as a special case of communication. This viewpoint was elaborated, for example, in the noisy channel model of machine translation. In practice, seq2seq maps an input sequence into a real-numerical vector by using a neural network (the encoder), and then maps it back to an output sequence using another neural network (the decoder). The idea of encoder-decoder sequence transduction had been developed in the early 2010s. The papers most commonly cited as the originators that produced seq2seq are two papers from 2014. In the seq2seq as proposed by them, both the encoder and the decoder were LSTMs. This had the "bottleneck" problem, since the encoding vector has a fixed size, so for long input sequences, information would tend to be lost, as they are difficult to fit into the fixed-length encoding vector. The attention mechanism, proposed in 2014, resolved the bottleneck problem. They called their model RNNsearch, as it "emulates searching through a source sentence during decoding a translation". A problem with seq2seq models at this point was that recurrent neural networks are difficult to parallelize. The 2017 publication of Transformers resolved the problem by replacing the encoding RNN with self-attention Transformer blocks ("encoder blocks"), and the decoding RNN with cross-attention causally-masked Transformer blocks ("decoder blocks"). === Priority dispute === One of the papers cited as the originator for seq2seq is (Sutskever et al 2014), published at Google Brain while they were on Google's machine translation project. The research allowed Google to overhaul Google Translate into Google Neural Machine Translation in 2016. Tomáš Mikolov claims to have developed the idea (before joining Google Brain) of using a "neural language model on pairs of sentences... and then [generating] translation after seeing the first sentence"—which he equates with seq2seq machine translation, and to have mentioned the idea to Ilya Sutskever and Quoc Le (while at Google Brain), who failed to acknowledge him in their paper. Mikolov had worked on RNNLM (using RNN for language modelling) for his PhD thesis, and is more notable for developing word2vec. == Architecture == The main reference for this section is. === Encoder === The encoder is responsible for processing the input sequence and capturing its essential information, which is stored as the hidden state of the network and, in a model with attention mechanism, a context vector. The context vector is the weighted sum of the input hidden states and is generated for every time instance in the output sequences. === Decoder === The decoder takes the context vector and hidden states from the encoder and generates the final output sequence. The decoder operates in an autoregressive manner, producing one element of the output sequence at a time. At each step, it considers the previously generated elements, the context vector, and the input sequence information to make predictions for the next element in the output sequence. Specifically, in a model with attention mechanism, the context vector and the hidden state are concatenated together to form an attention hidden vector, which is used as an input for the decoder. The seq2seq method developed in the early 2010s uses two neural networks: an encoder network converts an input sentence into numerical vectors, and a decoder network converts those vectors to sentences in the target language. The Attention mechanism was grafted onto this structure in 2014 and is shown below. Later it was refined into the encoder-decoder Transformer architecture of 2017. === Training vs prediction === There is a subtle difference between training and prediction. During training time, both the input and the output sequences are known. During prediction time, only the input sequence is known, and the output sequence must be decoded by the network itself. Specifically, consider an input sequence x 1 : n {\displaystyle x_{1:n}} and output sequence y 1 : m {\displaystyle y_{1:m}} . The encoder would process the input x 1 : n {\displaystyle x_{1:n}} step by step. After that, the decoder would take the output from the encoder, as well as the
Radioplayer
Radioplayer is a radio technology platform, owned by UK radio broadcasters and operated under licence in some other countries. It operates an internet radio web tuner, a set of mobile phone apps, an in-car adaptor, and a growing range of integrations with other connected devices and platforms. Radioplayer is operated by UK Radioplayer Ltd which is a not-for-profit organisation owned by UK radio broadcasters. Initial shareholders were the BBC, Global Radio, GMG Radio, Absolute Radio and RadioCentre. After consolidation in the radio market, current shareholders are the BBC, Global Radio, Bauer Media Group and RadioCentre. == History == Launched in the UK on 31 March 2011, Radioplayer set out to offer a simple and accessible way to listen to radio via the internet. It contained 157 stations at launch. Initially working internally at the BBC for Tim Davie, then Director of BBC Audio & Music, Michael Hill led the project since March 2009; he was made Managing Director of UK Radioplayer Ltd on 28 July 2010. At launch, Radioplayer was a simple and straightforward Flash-based radio player, linked-to by radio stations on their own website. The player included searching and bookmarking across all of UK radio station content. On 5 October 2012, Radioplayer launched a mobile app on iOS phones with an Android version following shortly afterwards. The apps are unavailable for download outside the United Kingdom. This was followed by a tablet app on 25 September 2013. The apps also support Android Wear, Android Auto, Smart Device Link, Apple Watch and Apple CarPlay. They are also compatible with Chromecast and Airplay. In September 2016, Radioplayer announced it had been chosen by Amazon to integrate with their new voice-controlled 'Echo' device, ahead of its UK launch. In July 2017, Radioplayer integrated with the Sonos and Bose multi-room speaker platforms. UK Radioplayer currently contains around 500 UK stations, from Ofcom-licensed broadcasters. Online-only 'sister-stations' can also be added, but only by broadcasters with Ofcom licences which have been on the platform for over a year. == Radioplayer Car == Radioplayer Car was announced in September 2014 as a hybrid radio receiver that switches between FM, DAB and streaming to find the strongest signal. Speaking in Oslo in June 2015, Michael Hill said that he hoped to launch the product in the UK and Norway during the summer of 2015. In February 2017, Radioplayer Car was launched. It was marketed as the world’s first voice-controlled hybrid radio adaptor for car stereos. A small box, fitted behind the dashboard, links to the auxiliary input on an existing car radio. It connects wirelessly via Bluetooth to the driver’s smartphone by an app. The adaptor enabled drivers to listen to their own smartphone music collections using Bluetooth, take hands-free calls, listen to inbound text messages and receive instant audio travel news, customised by GPS to their location and direction of travel. The hardware was manufactured under licence by car audio interfaces supplier Connects2, and Hyde Park Corner was promoted as the preferred installer of the audio equipment. There were several spin-off benefits of the Radioplayer Car project, including the creation of the hybrid radio metadata API for cars, known as the 'WRAPI' (Worldwide Radioplayer API). == International == Through a separate company called Radioplayer Worldwide, Radioplayer technology is licensed to a number of different territories.
Second-order co-occurrence pointwise mutual information
In computational linguistics, second-order co-occurrence pointwise mutual information (SOC-PMI) is a method used to measure semantic similarity, or how close in meaning two words are. The method does not require the two words to appear together in a text. Instead, it works by analyzing the "neighbor" words that typically appear alongside each of the two target words in a large body of text (corpus). If the two target words frequently share the same neighbors, they are considered semantically similar. For example, the words "cemetery" and "graveyard" may not appear in the same sentence often, but they both frequently appear near words like "buried," "dead," and "funeral." SOC-PMI uses this shared context to determine that they have a similar meaning. The method is called "second-order" because it doesn't look at the direct co-occurrence of the target words (which would be first-order), but at the co-occurrence of their neighbors (a second level of association). The strength of these associations is quantified using pointwise mutual information (PMI). == History == The method builds on earlier work like the PMI-IR algorithm, which used the AltaVista search engine to calculate word association probabilities. The key advantage of a second-order approach like SOC-PMI is its ability to measure similarity between words that do not co-occur often, or at all. The British National Corpus (BNC) has been used as a source for word frequencies and contexts for this method. == Methodology == The SOC-PMI algorithm measures the similarity between two words, w 1 {\displaystyle w_{1}} and w 2 {\displaystyle w_{2}} , in several steps. === Step 1: Score neighboring words with PMI === First, for each target word ( w 1 {\displaystyle w_{1}} and w 2 {\displaystyle w_{2}} ), the algorithm identifies its "neighbor" words within a certain text window (e.g., within 5 words to the left or right) across a large corpus. The strength of the association between a target word t i {\displaystyle t_{i}} and its neighbor w {\displaystyle w} is calculated using pointwise mutual information (PMI). A higher PMI value means the two words appear together more often than would be expected by chance. The PMI between a target word t i {\displaystyle t_{i}} and a neighbor word w {\displaystyle w} is calculated as: f pmi ( t i , w ) = log 2 f b ( t i , w ) × m f t ( t i ) f t ( w ) {\displaystyle f^{\text{pmi}}(t_{i},w)=\log _{2}{\frac {f^{b}(t_{i},w)\times m}{f^{t}(t_{i})f^{t}(w)}}} where: f b ( t i , w ) {\displaystyle f^{b}(t_{i},w)} is the number of times t i {\displaystyle t_{i}} and w {\displaystyle w} appear together in the context window. f t ( t i ) {\displaystyle f^{t}(t_{i})} is the total number of times t i {\displaystyle t_{i}} appears in the corpus. f t ( w ) {\displaystyle f^{t}(w)} is the total number of times w {\displaystyle w} appears in the corpus. m {\displaystyle m} is the total number of tokens (words) in the corpus. === Step 2: Create a semantic 'signature' for each word === For each target word ( w 1 {\displaystyle w_{1}} and w 2 {\displaystyle w_{2}} ), the algorithm creates a list of its most significant neighbors. This is done by taking the top β {\displaystyle \beta } neighbor words, sorted in descending order by their PMI score with the target word. This list of top neighbors, X w {\displaystyle X^{w}} , acts as a semantic "signature" for the word w {\displaystyle w} . X w = { X i w } {\displaystyle X^{w}=\{X_{i}^{w}\}} , for i = 1 , 2 , … , β {\displaystyle i=1,2,\ldots ,\beta } The size of this list, β {\displaystyle \beta } , is a parameter of the method. === Step 3: Compare the signatures === The algorithm then compares the signatures of w 1 {\displaystyle w_{1}} and w 2 {\displaystyle w_{2}} . It looks for words that are present in both signatures. The similarity of w 1 {\displaystyle w_{1}} to w 2 {\displaystyle w_{2}} is calculated by summing the PMI scores of w 2 {\displaystyle w_{2}} with every word in w 1 {\displaystyle w_{1}} 's signature list. The β {\displaystyle \beta } -PMI summation function defines this score. The score for w 1 {\displaystyle w_{1}} with respect to w 2 {\displaystyle w_{2}} is: f ( w 1 , w 2 , β ) = ∑ i = 1 β ( f pmi ( X i w 1 , w 2 ) ) γ {\displaystyle f(w_{1},w_{2},\beta )=\sum _{i=1}^{\beta }(f^{\text{pmi}}(X_{i}^{w_{1}},w_{2}))^{\gamma }} This sum only includes terms where the PMI value is positive. The exponent γ {\displaystyle \gamma } (with a value > 1) is used to give more weight to neighbors that are more strongly associated with w 2 {\displaystyle w_{2}} . This calculation is done in both directions: The similarity of w 1 {\displaystyle w_{1}} with respect to w 2 {\displaystyle w_{2}} : f ( w 1 , w 2 , β 1 ) = ∑ i = 1 β 1 ( f pmi ( X i w 1 , w 2 ) ) γ {\displaystyle f(w_{1},w_{2},\beta _{1})=\sum _{i=1}^{\beta _{1}}(f^{\text{pmi}}(X_{i}^{w_{1}},w_{2}))^{\gamma }} The similarity of w 2 {\displaystyle w_{2}} with respect to w 1 {\displaystyle w_{1}} : f ( w 2 , w 1 , β 2 ) = ∑ i = 1 β 2 ( f pmi ( X i w 2 , w 1 ) ) γ {\displaystyle f(w_{2},w_{1},\beta _{2})=\sum _{i=1}^{\beta _{2}}(f^{\text{pmi}}(X_{i}^{w_{2}},w_{1}))^{\gamma }} === Step 4: Calculate final similarity score === Finally, the total semantic similarity is the average of the two scores from the previous step. S i m ( w 1 , w 2 ) = f ( w 1 , w 2 , β 1 ) β 1 + f ( w 2 , w 1 , β 2 ) β 2 {\displaystyle \mathrm {Sim} (w_{1},w_{2})={\frac {f(w_{1},w_{2},\beta _{1})}{\beta _{1}}}+{\frac {f(w_{2},w_{1},\beta _{2})}{\beta _{2}}}} This score can be normalized to fall between 0 and 1. For example, using this method, the words cemetery and graveyard achieve a high similarity score of 0.986 (with specific parameter settings).