Pixorial

Pixorial was a cloud-based consumer photo sharing, video sharing and video editing platform. The company was formed in 2007 in Centennial, Colorado as a media conversion service. In 2013, Pixorial was chosen as one of two video storage companies to partner with the launch of Google Drive. Pixorial allowed users to edit and share videos on social channels by connecting through their Pixorial account. The company closed on July 18, 2014, and its assets were acquired by LifeLogger Technologies Corp in November 2015. == History == The company was founded in 2007 and launched in 2009 by former Netscape employee Andres Espineira. Changing its focus to video editing software in 2009, Pixorial began developing an app that would be launched for iOS and Android devices in 2011. Later developments in the app in 2012 would also included real time filters, which were later removed. With the launch of Google Drive in 2012, Pixorial was chosen as an integrated video partner. This integration with Google Drive allowed users to access videos stored in Google Drive within the web app of Pixorial. After the Google Drive launch, Pixorial developed a crowdsourced, location-based video sharing app, Krowds. The app was cited in July 2012 by PC Magazine as one of "The 8 Best Apps for Making and Sharing Videos on Your iPhone". In late July, Pixorial replaced its original mobile app with the MyPlayer HD app that optimized HD video viewing for large screen viewing including tablets and smart televisions. Pixorial's services terminated on July 18, 2014. == Products == === Krowds App === Pixorial's app was launched in April 2013 for iOS, and in May for Android, as a tool to aggregate event videos through location based collections. The app was launched to generally positive reviews. === Movie Creator === Launched July 12, 2012 Pixorial's Movie Creator allowed users to edit movies in a simple story-telling platform Movie Creator's features include transitions, text boxes, access to free music tracks, credits, and social media sharing capabilities. The Pixorial platform allowed users to view, share, and edit videos without modifying the original. Movie Creator integrated pictures and video to create user movies. == Awards == 2012 Apex Award from the Colorado Technology Association, for Best Technology Project of the Year 2010 Computerworld Laureate for Media, Arts and Entertainment

ReRites

ReRites (also known as RERITES, ReadingRites, Big Data Poetry) is a literary work of "Human + A.I. poetry" by David Jhave Johnston that used neural network models trained to generate poetry which the author then edited. ReRites won the Robert Coover Award for a Work of Electronic Literature in 2022. == About the project == The ReRites project began as a daily rite of writing with a neural network, expanded into a series of performances from which video documentation has been published online, and concluded with a set of 12 books and an accompanying book of essays published by Anteism Books in 2019. In Electronic Literature, Scott Rettberg describes the early phases of the project in 2016, when it bore the preliminary name Big Data Poetry. Jhave (the artist name that David Jhave Johnston goes by) describes the process of writing ReRites as a rite: "Every morning for 2 hours (normally 6:30–8:30am) I get up and edit the poetic output of a neural net. Deleting, weaving, conjugating, lineating, cohering. Re-writing. Re-wiring authorship: hybrid augmented enhanced evolutionary". There is video documentation of the writing process. The human editing of the neural network's output is fundamental to this project, and Jhave gives examples of both unedited text extracts and his edited versions in publications about the project. Kyle Booten describes ReRites as "simultaneously dusty and outrageously verdant, monotonously sublime and speckled with beautiful and rare specimens". === Performances === ReRites was first shared with an audience through a series of performances where audience members and poets would participate in reading the automatically generated texts, which appeared on screen so fast that human readers could barely keep up. This has been described as allowing participants to "re-discover[..] the peculiar pleasures of being embodied", or, in Jhave's own words, as a space where human participants were "playing their wits and voices against an evocative infinite deep-learning muse". The first performance was at Brown University's Interrupt Festival in 2019. It has been performed many times since, including at the Barbican Centre in London and Anteism Books. === Print publications === For a single year Jhave published one book of poetry from the ReRites project each month. These twelve volumes are accompanied by a book of essays, all published by Anteism Books. The accompanying essays provide critical responses to the project from poets and scholars including Allison Parrish, Johanna Drucker, Kyle Booten, Stephanie Strickland, John Cayley, Lai-Tze Fan, Nick Montfort, Mairéad Byrne, and Chris Funkhouser. Allison Parrish notes elsewhere that these paratexts to ReRites serve a legitimising function for a genre of poetry that is not yet institutionally acknowledged. === Technical details === Starting in 2016 under the name Big Data Poetry, Jhave generated poems using, in his own words, "neural network code (..) adapted from three corporate github-hosted machine-learning libraries: TensorFlow (Google), PyTorch (Facebook), and AWD-LSTM (SalesForce)". He explains that the "models were trained on a customised corpus of 600,000 lines of poetry ranging from the romantic epoch to the 20th century avant garde". Jhave maintains a GitHub repository with some of the code supporting ReRites. == Reception == ReRites is described by John Cayley as "one of the most thorough and beautiful" poetic responses to machine learning. The work's influence on the field of electronic literature was acknowledged in 2022, when the work won the Electronic Literature Organization's Robert Coover Award for a Work of Electronic Literature. The jury described ReRites as particularly poignant in the time of the pandemic, as it was "a documentation of the performance of the private ritual of writing and the obsessive-compulsive need for writers to communicate — even when no one else is reading". The question of authorship and voice in ReRites has been raised by several critics. Although generated poetry is an established genre in electronic literature, Cayley notes that unlike the combinatory poems created by authors like Nick Montfort, where the author explicitly defines which words and phrases will be recombined, ReRites has "not been directed by literary preconceptions inscribed in the program itself, but only by patterns and rhythms pre-existing in the corpora". In an essay for the Australian journal TEXT, David Thomas Henry Wright asks how to understand authorship and authority in ReRites: "Who or what is the authority of the work? The original data fed into the machine, that is not currently retrievable or discernible from the final works? The code that was taken and adapted for his purposes? Or Jhave, the human editor?" Wright concludes that Jhave is the only actor with any intentionality and therefore the authority of the work. The centrality of the human editor is also emphasised by other scholars. In a chapter analysing ReRites Malthe Stavning Erslev argues that the machine learning misrepresents the dataset it is trained on. While ReRites uses 21st century neural networks, it has been compared to earlier literary traditions. Poet Victoria Stanton, who read at one of the ReRites performances, has compared ReRites to found poetry, while David Thomas Henry Wright compares it to the Oulipo movement and Mark Amerika to the cut-up technique. Scholars also position ReRites firmly within the long tradition of generative poetry both in electronic literature and print, stretching from the I Ching, Queneau's Cent Mille Milliards de Poemes and Nabokov's Pale Fire to computer-generated poems like Christopher Strachey's Love Letter Generator (1952) and more contemporary examples. Jhave describes the process of working with the output from the neural network as "carving". In his book My Life as an Artificial Creative Intelligence, Mark Amerika writes that the "method of carving the digital outputs provided by the language model as part of a collaborative remix jam session with GPT-2, where the language artist and the language model play off each other’s unexpected outputs as if caught in a live postproduction set, is one I share with electronic literature composer David Jhave Johnston, whose AI poetry experiments precede my own investigations."

Executive Order 14179

Executive Order 14179, titled "Removing Barriers to American Leadership in Artificial Intelligence", is an executive order signed by Donald Trump, the 47th President of the United States, on January 23, 2025. The executive order aims to initiate the process of strengthening U.S. leadership in artificial intelligence, promote AI development free from ideological bias or social agendas, establish an action plan to maintain global AI dominance, and to revise or rescind policies that conflict with these goals. == Background == === Joe Biden === This executive order comes in response to the Executive Order 14110 titled Executive Order on Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence (sometimes referred to as "Executive Order on Artificial Intelligence") signed by Joe Biden on October 30, 2023. === Donald Trump === Donald Trump rescinded Executive Order 14110 on his first day in office with the Initial Rescissions of Harmful Executive Orders and Actions executive order. On January 23, 2025, Trump signed the Removing Barriers to American Leadership in Artificial Intelligence executive order as the replacement executive order covering the development of artificial intelligence technologies. == Provisions == It revokes existing AI policies and directives that are seen as barriers to U.S. AI innovation. It mandates the creation of an action plan within 180 days to sustain U.S. AI leadership, focusing on human flourishing, economic competitiveness, and national security. It requires the review of policies, directives, and regulations related to Executive Order 14110 (from October 2023) to identify actions that may conflict with the new policy goals. Agencies are instructed to suspend, revise, or rescind actions from the previous executive order that may be inconsistent with the new policy. The Office of Management and Budget (OMB) must revise certain memoranda (M-24-10 and M-24-18) within 60 days to align with the new policy. The order specifies that it does not create new enforceable rights or benefits and should be implemented within the boundaries of existing law and appropriations. == Implementation == The NITRD program, on behalf of the Office of Science and Technology Policy (OSTP), requested public input on the development of an AI Action Plan by March 15. == Reactions == Over 10,000 public comments were submitted in response to the OSTP request for public input. OpenAI submitted comments proposing a five-point strategy focused on regulatory preemption, export controls, copyright protections, infrastructure investment, and government adoption to ensure AI innovation, promote democratic AI globally, and protect national security. They emphasized the ability to learn from copyrighted material to maintain America's lead against China's state-controlled AI efforts like DeepSeek. Google submitted comments advocating for a three-pronged plan that invests in domestic AI development through energy infrastructure reform, balanced export controls, continued research funding, and coherent federal policies, while modernizing government AI adoption and promoting innovation-friendly approaches internationally. Both OpenAI and Google urged White House opposition to foreign copyright and transparency obligations, for example in the UK Government's preferred option in their Copyright and AI consultation.

SHRDLU

SHRDLU is an early natural-language understanding computer program that was developed by Terry Winograd at MIT in 1968–1970. In the program, the user carries on a conversation with the computer, moving objects, naming collections and querying the state of a simplified "blocks world", essentially a virtual box filled with different blocks. SHRDLU was written in the Micro Planner and Lisp programming language on the DEC PDP-6 computer and a DEC graphics terminal. Later additions were made at the computer graphics labs at the University of Utah, adding a full 3D rendering of SHRDLU's "world". The name SHRDLU was derived from ETAOIN SHRDLU, the arrangement of the letter keys on a Linotype machine, arranged in descending order of usage frequency in English. == Functionality == SHRDLU is primarily a language parser that allows user interaction using English terms. The user instructs SHRDLU to move various objects around in the "blocks world" containing various basic objects such as blocks, cones and balls. SHRDLU combined four simple ideas to make the simulation of "understanding" more convincing. One was that SHRDLU's world is so simple that the entire set of objects and locations could be described by including as few as 50 words: nouns like "block" and "cone", verbs like "place on" and "move to", and adjectives like "big" and "blue". The possible combinations of these basic language building blocks are quite simple. SHRDLU also includes a basic memory to supply context. One could ask SHRDLU to "put the green cone on the red block" and then "take the cone off"; "the cone" would be taken to mean the green cone one had just talked about. SHRDLU can search back further through the interactions to find the proper context in most cases when additional adjectives were supplied. One could also ask questions about the history; for instance, one could ask "did you pick up anything before the cone?" A side effect of this memory, and the original rules SHRDLU was supplied with, is that the program can answer questions about what was possible in the world and what was not. For instance, SHRDLU can deduce that blocks could be stacked by looking for examples, but also realize that triangles could not be stacked, after having tried it. The "world" contains basic physics to make blocks fall over, independent of the language parser. Finally, SHRDLU can also remember names given to objects, or arrangements of them. For instance one could say "a steeple is a small triangle on top of a tall rectangle"; SHRDLU can then answer questions about steeples in the blocks world, and build new ones. This is an example of a SHRDLU session: Person: Pick up a big red block. Computer: OK. Person: Grasp the pyramid. Computer: I DON'T UNDERSTAND WHICH PYRAMID YOU MEAN. Person (changing their mind): Find a block which is taller than the one you are holding and put it into the box. Computer: BY "IT", I ASSUME YOU MEAN THE BLOCK WHICH IS TALLER THAN THE ONE I AM HOLDING. Computer: OK. Person: What does the box contain? Computer: THE BLUE PYRAMID AND THE BLUE BLOCK. Person: What is the pyramid supported by? Computer: THE BOX. Person: How many blocks are not in the box? Computer: FOUR OF THEM. Person: Is at least one of them narrower than the one which i told you to pick up? Computer: YES, THE RED CUBE. Person: Is it supported? Computer: YES, BY THE TABLE. Person: Can the table pick up blocks? Computer: NO. Person: Can a pyramid be supported by a block? Computer: YES. Person: Can a pyramid support a pyramid? Computer: I DON'T KNOW. Person: Stack up two pyramids. Computer: I CAN'T. Person: Will you please stack up both of the red blocks and either a green cube or a pyramid? Computer: OK. Person: Which cube is sitting on the table? Computer: THE LARGE GREEN ONE WHICH SUPPORTS THE RED PYRAMID. Person: Is there a large block behind a pyramid? Computer: YES, THREE OF THEM: A LARGE RED ONE, A LARGE GREEN CUBE, AND THE BLUE ONE. Person: Put a small one onto the green cube which supports a pyramid. Computer: OK. Person: Put the littlest pyramid on top of it. Computer: OK. Person: Does the shortest thing the tallest pyramid's support supports support anything green? Computer: YES, THE GREEN PYRAMID. Person: What color is it? Computer: BY "IT", I ASSUME YOU MEAN THE SHORTEST THING THE TALLEST PYRAMID'S SUPPORT SUPPORTS. Computer: RED Person: How many things are on top of green cubes? Computer: I'M NOT SURE WHAT YOU MEAN BY "ON TOP OF" IN THE PHRASE "ON TOP OF GREEN CUBES" . DO YOU MEAN: 1 - DIRECTLY ON THE SURFACE 2 - ANWHERE ON TOP OF ? Person: 2 Computer: THREE OF THEM. Person: Had you touched any pyramid before you put the green one on the little cube? Computer: YES, THE GREEN ONE. Person: When did you pick it up? Computer: WHILE I WAS STACKING UP THE RED CUBE, A LARGE RED BLOCK AND A LARGE GREEN CUBE. Person: Why? Computer: TO GET RID OF IT. Person: Why did you do that? Computer: TO CLEAN OFF THE RED CUBE. Person: Why did you clear off that cube? Computer: TO PUT IT ON A LARGE GREEN CUBE. Person: Why did you do that? Computer: TO STACK UP THE RED CUBE , A LARGE RED BLOCK AND A LARGE GREEN CUBE. Person: Why did you do that? Computer: BECAUSE YOU ASKED ME TO. Person: How did you do it? Computer: BY PUTTING A LARGE RED BLOCK ON THE TABLE ; THEN LETTING GO OF IT ; THEN PUTTING A LARGE GREEN CUBE ON IT ; THEN LETTING GO OF THAT CUBE ; THEN PUTTING THE RED CUBE ON THAT CUBE; THEN LETTING GO OF THAT CUBE. Person: How many objects did you touch while you were doing it? Computer: FOUR OF THEM. Person: What did the red cube support before you started to clean it off? Computer: THE GREEN PYRAMID. Person: There were five blocks to the left of the box then. Computer: NO, ONLY FOUR OF THEM: THE RED CUBE, TWO LARGE GREEN CUBES AND A LARGE RED BLOCK. Person: Put the blue pyramid on the block in the box. Computer: OK. Person: Is there anything which is bigger than every pyramid but is not as wide as the thing that supports it? Computer: YES, THE BLUE BLOCK. Person: Does a steeple Computer (interrupting): SORRY, I DON'T KNOW THE WORD "STEEPLE". Person: A "steeple" is a stack which contains two green cubes and a pyramid. Computer: I UNDERSTAND. Person: Are there any steeples now? Computer: NO. Person: Build one. Computer: OK. Person: Call the biggest block "superblock". Computer: OK. Person: Have you picked superblock up since we began? Computer: YES. Person: Why did you drop it? Computer: BY "IT", I ASSUME YOU MEAN THE SUPERBLOCK. I CAN'T EXPLAIN A NON-EXISTENT EVENT. Person: Is there anything to the right of the red pyramid? Computer: YES, FOUR THINGS: THE BOX, THE RED CUBE, THE BLUE PYRAMID AND THE BLOCK NAMED SUPERBLOCK Person: Thank you. Computer: YOU'RE WELCOME! == Consequences == SHRDLU was considered a tremendously successful demonstration of artificial intelligence (AI). This led other AI researchers to excessive optimism which was soon lost when later systems attempted to deal with situations with a more realistic level of ambiguity and complexity. Subsequent efforts of the SHRDLU type, such as Cyc, have tended to focus on providing the program with considerably more information from which it can draw conclusions. In a 1991 interview, Winograd said about SHRDLU: [...] the famous dialogue with SHRDLU where you could pick up a block, and so on, I very carefully worked through, line by line. If you sat down in front of it, and asked it a question that wasn't in the dialogue, there was some probability it would answer it. I mean, if it was reasonably close to one of the questions that was there in form and in content, it would probably get it. But there was no attempt to get it to the point where you could actually hand it to somebody and they could use it to move blocks around. And there was no pressure for that whatsoever. Pressure was for something you could demo. Take a recent example, Negroponte's Media Lab, where instead of "perish or publish" it's "demo or die." I think that's a problem. I think AI suffered from that a lot, because it led to "Potemkin villages", things which - for the things they actually did in the demo looked good, but when you looked behind that there wasn't enough structure to make it really work more generally. Though not intentionally developed as such, SHRDLU is considered the first known formal example of interactive fiction, as the user interacts with simple commands to move objects around a virtual environment, though lacking the distinct story-telling normally present in the interactive fiction genre. The 1976-1977 game Colossal Cave Adventure is broadly considered to be the first true work of interactive fiction.

Catastrophic interference

Catastrophic interference, also known as catastrophic forgetting, is the tendency of an artificial neural network to abruptly and drastically forget previously learned information upon learning new information. Neural networks are an important part of the connectionist approach to cognitive science. The issue of catastrophic interference when modeling human memory with connectionist models was originally brought to the attention of the scientific community by research from McCloskey and Cohen (1989), and Ratcliff (1990). It is a radical manifestation of the 'sensitivity-stability' dilemma or the 'stability-plasticity' dilemma. Specifically, these problems refer to the challenge of making an artificial neural network that is sensitive to, but not disrupted by, new information. Lookup tables and connectionist networks lie on the opposite sides of the stability plasticity spectrum. The former remains completely stable in the presence of new information but lacks the ability to generalize, i.e. infer general principles, from new inputs. On the other hand, connectionist networks like the standard backpropagation network can generalize to unseen inputs, but they are sensitive to new information. Backpropagation models can be analogized to human memory insofar as they have a similar ability to generalize, but these networks often exhibit less stability than human memory. Notably, these backpropagation networks are susceptible to catastrophic interference. This is an issue when modelling human memory, because unlike these networks, humans typically do not show catastrophic forgetting. == Discovery == The term catastrophic interference was originally coined by McCloskey and Cohen (1989) but was also brought to the attention of the scientific community by research from Ratcliff (1990). === The Sequential Learning Problem: McCloskey and Cohen (1989) === McCloskey and Cohen (1989) noted the problem of catastrophic interference during two different experiments with backpropagation neural network modelling. Experiment 1: Learning the ones and twos addition facts In their first experiment they trained a standard backpropagation neural network on a single training set consisting of 17 single-digit ones problems (i.e., 1 + 1 through 9 + 1, and 1 + 2 through 1 + 9) until the network could represent and respond properly to all of them. The error between the actual output and the desired output steadily declined across training sessions, which reflected that the network learned to represent the target outputs better across trials. Next, they trained the network on a single training set consisting of 17 single-digit twos problems (i.e., 2 + 1 through 2 + 9, and 1 + 2 through 9 + 2) until the network could represent, respond properly to all of them. They noted that their procedure was similar to how a child would learn their addition facts. Following each learning trial on the twos facts, the network was tested for its knowledge on both the ones and twos addition facts. Like the ones facts, the twos facts were readily learned by the network. However, McCloskey and Cohen noted the network was no longer able to properly answer the ones addition problems even after one learning trial of the twos addition problems. The output pattern produced in response to the ones facts often resembled an output pattern for an incorrect number more closely than the output pattern for a correct number. This is considered to be a drastic amount of error. Furthermore, the problems 2+1 and 1+2, which were included in both training sets, even showed dramatic disruption during the first learning trials of the twos facts. Experiment 2: Replication of Barnes and Underwood (1959) study In their second connectionist model, McCloskey and Cohen attempted to replicate the study on retroactive interference in humans by Barnes and Underwood (1959). They trained the model on A-B and A-C lists and used a context pattern in the input vector (input pattern), to differentiate between the lists. Specifically the network was trained to respond with the right B response when shown the A stimulus and A-B context pattern and to respond with the correct C response when shown the A stimulus and the A-C context pattern. When the model was trained concurrently on the A-B and A-C items then the network readily learned all of the associations correctly. In sequential training the A-B list was trained first, followed by the A-C list. After each presentation of the A-C list, performance was measured for both the A-B and A-C lists. They found that the amount of training on the A-C list in Barnes and Underwood study that lead to 50% correct responses, lead to nearly 0% correct responses by the backpropagation network. Furthermore, they found that the network tended to show responses that looked like the C response pattern when the network was prompted to give the B response pattern. This indicated that the A-C list apparently had overwritten the A-B list. This could be likened to learning the word dog, followed by learning the word stool and then finding that you think of the word stool when presented with the word dog. McCloskey and Cohen tried to reduce interference through a number of manipulations including changing the number of hidden units, changing the value of the learning rate parameter, overtraining on the A-B list, freezing certain connection weights, changing target values 0 and 1 instead 0.1 and 0.9. However, none of these manipulations satisfactorily reduced the catastrophic interference exhibited by the networks. Overall, McCloskey and Cohen (1989) concluded that: at least some interference will occur whenever new learning alters the weights involved in representing old learning the greater the amount of new learning, the greater the disruption in old knowledge interference was catastrophic in the backpropagation networks when learning was sequential but not concurrent === Constraints Imposed by Learning and Forgetting Functions: Ratcliff (1990) === Ratcliff (1990) used multiple sets of backpropagation models applied to standard recognition memory procedures, in which the items were sequentially learned. After inspecting the recognition performance models he found two major problems: Well-learned information was catastrophically forgotten as new information was learned in both small and large backpropagation networks. Even one learning trial with new information resulted in a significant loss of the old information, paralleling the findings of McCloskey and Cohen (1989). Ratcliff also found that the resulting outputs were often a blend of the previous input and the new input. In larger networks, items learned in groups (e.g. AB then CD) were more resistant to forgetting than were items learned singly (e.g. A then B then C...). However, the forgetting for items learned in groups was still large. Adding new hidden units to the network did not reduce interference. Discrimination between the studied items and previously unseen items decreased as the network learned more. This finding contradicts studies on human memory, which indicated that discrimination increases with learning. Ratcliff attempted to alleviate this problem by adding 'response nodes' that would selectively respond to old and new inputs. However, this method did not work as these response nodes would become active for all inputs. A model which used a context pattern also failed to increase discrimination between new and old items. == Proposed solutions == The main cause of catastrophic interference seems to be overlap in the representations at the hidden layer of distributed neural networks. In a distributed representation, each input tends to create changes in the weights of many of the nodes. Catastrophic forgetting occurs because when many of the weights where "knowledge is stored" are changed, it is unlikely for prior knowledge to be kept intact. During sequential learning, the inputs become mixed, with the new inputs being superimposed on top of the old ones. Another way to conceptualize this is by visualizing learning as a movement through a weight space. This weight space can be likened to a spatial representation of all of the possible combinations of weights that the network could possess. When a network first learns to represent a set of patterns, it finds a point in the weight space that allows it to recognize all of those patterns. However, when the network then learns a new set of patterns, it will move to a place in the weight space for which the only concern is the recognition of the new patterns. To recognize both sets of patterns, the network must find a place in the weight space suitable for recognizing both the new and the old patterns. Below are a number of techniques which have empirical support in successfully reducing catastrophic interference in backpropagation neural networks: === Orthogonality === Many of the early techniques in reducing representational overlap involved making either the input vecto

Hybrid machine translation

Hybrid machine translation is a method of machine translation that is characterized by the use of multiple machine translation approaches within a single machine translation system. The motivation for developing hybrid machine translation systems stems from the failure of any single technique to achieve a satisfactory level of accuracy. Many hybrid machine translation systems have been successful in improving the accuracy of the translations, and there are several popular machine translation systems which employ hybrid methods. == Approaches == === Multi-engine === This approach to hybrid machine translation involves running multiple machine translation systems in parallel. The final output is generated by combining the output of all the sub-systems. Most commonly, these systems use statistical and rule-based translation subsystems, but other combinations have been explored. For example, researchers at Carnegie Mellon University have had some success combining example-based, transfer-based, knowledge-based and statistical translation sub-systems into one machine translation system. === Statistical rule generation === This approach involves using statistical data to generate lexical and syntactic rules. The input is then processed with these rules as if it were a rule-based translator. This approach attempts to avoid the difficult and time-consuming task of creating a set of comprehensive, fine-grained linguistic rules by extracting those rules from the training corpus. This approach still suffers from many problems of normal statistical machine translation, namely that the accuracy of the translation will depend heavily on the similarity of the input text to the text of the training corpus. As a result, this technique has had the most success in domain-specific applications, and has the same difficulties with domain adaptation as many statistical machine translation systems. === Multi-Pass === This approach involves serially processing the input multiple times. The most common technique used in multi-pass machine translation systems is to pre-process the input with a rule-based machine translation system. The output of the rule-based pre-processor is passed to a statistical machine translation system, which produces the final output. This technique is used to limit the amount of information a statistical system need consider, significantly reducing the processing power required. It also removes the need for the rule-based system to be a complete translation system for the language, significantly reducing the amount of human effort and labor necessary to build the system. === Confidence-Based === This approach differs from the other hybrid approaches in that in most cases only one translation technology is used. A confidence metric is produced for each translated sentence from which a decision can be made whether to try a secondary translation technology or to proceed with the initial translation output. SMT is also used when common error patterns such as multiple repeat words appear in sequence, as is common with NMT when the attention mechanism is confused.

Chinese room

The Chinese room argument holds that a computer executing a program cannot have a mind, understanding, or consciousness, regardless of how intelligently or human-like the program may make the computer behave. The argument was presented in a 1980 paper by the American philosopher John Searle, entitled "Minds, Brains, and Programs" and published in the journal Behavioral and Brain Sciences. Similar arguments had been made previously by others, including Gottfried Wilhelm Leibniz, Peter Winch, and Anatoly Dneprov. Searle's version has been widely discussed in the years since. The centerpiece of Searle's argument is a thought experiment known as the "Chinese room". The argument is directed against the philosophical positions of functionalism and computationalism, which hold that the mind may be viewed as an information-processing system operating on formal symbols, and that simulation of a given mental state is sufficient for its presence. Specifically, the argument is intended to refute a position Searle calls the strong AI hypothesis: "The appropriately programmed computer with the right inputs and outputs would thereby have a mind in exactly the same sense human beings have minds." Although its proponents originally presented the argument in reaction to statements of artificial intelligence (AI) researchers, it is not an argument against the goals of mainstream AI research because it does not show a limit in the amount of intelligent behavior a machine can display. The argument applies only to digital computers running programs and does not apply to machines in general. While widely discussed, the argument has been subject to significant criticism and remains controversial among philosophers of mind and AI researchers. == Chinese room thought experiment == Suppose that artificial intelligence research has succeeded in programming a computer to behave as if it understands Chinese. The machine accepts Chinese characters as input, carries out each instruction of the program step by step, and then produces Chinese characters as output. The machine does this so perfectly that no one can tell that they are communicating with a machine and not a hidden Chinese speaker. The questions at issue are these: does the machine actually understand the conversation, or is it just simulating the ability to understand the conversation? Does the machine have a mind in exactly the same sense that people do, or is it just acting as if it had a mind? Now suppose that Searle is in a room with an English version of the program, along with sufficient pencils, paper, erasers and filing cabinets. Chinese characters are slipped in under the door, and he follows the program step-by-step, which eventually instructs him to slide other Chinese characters back out under the door. If the computer had passed the Turing test this way, it follows that Searle would do so as well, simply by running the program by hand. Searle can see no essential difference between the roles of the computer and himself in the experiment. Each simply follows a program, step-by-step, producing behavior that makes them appear to understand. However, Searle would not be able to understand the conversation. Therefore, he argues, it follows that the computer would not be able to understand the conversation either. Searle argues that, without "understanding" (or "intentionality"), we cannot describe what the machine is doing as "thinking" and, since it does not think, it does not have a "mind" in the normal sense of the word. Therefore, he concludes that the strong AI hypothesis is false: a computer running a program that simulates a mind would not have a mind in the same sense that human beings have a mind. == History == Gottfried Wilhelm Leibniz made a similar argument in 1713 against mechanism, the idea that everything that makes up a human being could, in principle, be explained in mechanical terms—in other words, that a person, including their mind, is merely a very complex machine. Leibniz used the thought experiment of expanding the brain until it was the size of a mill. He found it difficult to imagine that a "mind" capable of "perception" could be constructed using only mechanical processes. British philosopher Peter Winch made the same point in his 1958 book The Idea of a Social Science and its Relation to Philosophy, in which he argues that "a man who understands Chinese is not a man who has a firm grasp of the statistical probabilities for the occurrence of the various words in the Chinese language" (p. 108). Soviet cyberneticist Anatoly Dneprov made an essentially identical argument in 1961, in the form of his short story "The Game". In it, a stadium of people act as switches and memory cells implementing a program to translate a sentence from Portuguese, a language none of them know. The game was organized by a "Professor Zarubin" to answer the question "Can mathematical machines think?" Speaking through Zarubin, Dneprov writes that "the only way to prove that machines can think is to turn yourself into a machine and examine your thinking process", and he concludes, as Searle does, that "even the most perfect simulation of machine thinking is not the thinking process itself." In 1974, Lawrence H. Davis imagined duplicating the brain using telephone lines and offices staffed by people, and in 1978, Ned Block envisioned the entire population of China involved in such a brain simulation. This is known as the China brain thought experiment. Searle's version appeared in his 1980 article "Minds, Brains, and Programs", published in Behavioral and Brain Sciences. It eventually became the journal's "most influential target article", generating an enormous number of commentaries and responses in the ensuing decades, and Searle had continued to defend and refine the argument in multiple papers, popular articles, and books. David Cole writes that "the Chinese Room argument has probably been the most widely discussed philosophical argument in cognitive science to appear in the past 25 years". Most of the discussion consists of attempts to refute it. "The overwhelming majority", notes Behavioral and Brain Sciences editor Stevan Harnad, "still think that the Chinese Room Argument is dead wrong". The sheer volume of the literature that has grown up around it inspired Pat Hayes to comment that the field of cognitive science ought to be redefined as "the ongoing research program of showing Searle's Chinese Room Argument to be false". Searle's argument has become "something of a classic in cognitive science", according to Harnad. Varol Akman agrees, and has described the original paper as "an exemplar of philosophical clarity and purity". == Philosophy == Although the Chinese Room argument was originally presented in reaction to the statements of artificial intelligence researchers, philosophers have come to consider it as an important part of the philosophy of mind. It is a challenge to functionalism and the computational theory of mind, and is related to such questions as the mind–body problem, the problem of other minds, the symbol grounding problem, and the hard problem of consciousness. === Strong AI === Searle identified a philosophical position he calls "strong AI": The appropriately programmed computer with the right inputs and outputs would thereby have a mind in exactly the same sense human beings have minds. The definition depends on the distinction between simulating a mind and actually having one. Searle writes that "according to Strong AI, the correct simulation really is a mind. According to Weak AI, the correct simulation is a model of the mind." The claim is implicit in some of the statements of early AI researchers and analysts. For example, in 1957, the economist and psychologist Herbert A. Simon declared that "there are now in the world machines that think, that learn and create". Simon, together with Allen Newell and Cliff Shaw, after having completed the first program that could do formal reasoning (the Logic Theorist), claimed that they had "solved the venerable mind–body problem, explaining how a system composed of matter can have the properties of mind." John Haugeland wrote that "AI wants only the genuine article: machines with minds, in the full and literal sense. This is not science fiction, but real science, based on a theoretical conception as deep as it is daring: namely, we are, at root, computers ourselves." Searle also ascribes the following claims to advocates of strong AI: AI systems can be used to explain the mind; The study of the brain is irrelevant to the study of the mind; and The Turing test is adequate for establishing the existence of mental states. === Strong AI as computationalism or functionalism === In more recent presentations of the Chinese room argument, Searle has identified "strong AI" as "computer functionalism" (a term he attributes to Daniel Dennett). Functionalism is a position in modern philosophy of mind that holds that we can define menta