In a recent blog post, Baidu, the Chinese search engine and e-commerce giant, announced their latest open-source, natural language understanding framework called ERNIE 2.0. They also shared recent test results, including achieving state-of-the art (SOTA) results and outperforming existing frameworks, including Google's BERT and XLNet in 16 NLP tasks in both Chinese and English. ERNIE 2.0, more formally known as Enhanced Representation through kNowledge IntEgration, is a continual pre-training framework for language understanding. We proposed a continual pre-training framework for language understanding in which pre-training tasks can be incrementally built and learned through constant multi-task learning. In this framework, different customized tasks can be incrementally introduced at any time and are trained through multi-task learning that permits the encoding of lexical, syntactic and semantic information across tasks.
However, besides co-occurrence, there is other valuable lexical, syntactic and semantic information in training corpora. For example, named entities, such as names, locations and organizations, could contain conceptual information. Sentence order and proximity between sentences would allow models to learn structure-aware representations. What's more, semantic similarity at the document level or discourse relations among sentences could train the models to learn semantic-aware representations. Hypothetically speaking, would it be possible to further improve performance if the model was trained to constantly learn a larger variety of tasks?
In the very basic form, Natural language processing is a field of Artificial Intelligence that explores computational methods for interpreting and processing natural language, in either textual or spoken form. In this series of 2 blogs I'll be discussing Natural Language Processing, NLTK in Spark, environment setup and some basic implementations in the first one, and how we can create an NLP application which is leveraging the benefits of Bigdata in the second. A Natural language or Ordinary language is any language that has evolved naturally with time in humans through use and repetition without conscious planning or premeditation. Natural languages can take different forms, such as speech, signing or text. Signs, Menus, Email, SMS, Web Page and so much more… The list is endless.
Lexical semantics (also known as lexicosemantics), is a subfield of linguistic semantics. The units of analysis in lexical semantics are lexical units which include not only words but also sub-words or sub-units such as affixes and even compound words and phrases. Lexical units make up the catalogue of words in a language, the lexicon. Lexical semantics looks at how the meaning of the lexical units correlates with the structure of the language or syntax. This is referred to as syntax-semantic interface. Lexical units, also referred to as syntactic atoms, can stand alone such as in the case of root words or parts of compound words or they necessarily attach to other units such as prefixes and suffixes do. The former are called free morphemes and the latter bound morphemes.
Artificial Intelligence is making the transition to electronic-only publishing a necessity for textbook publishers. In a recent story, the BBC reported on how Pearsons, one of the largest textbook publishing companies in the world, is getting out of the print business. This is very much along the lines of Ford Motor Company announcing recently that they will stop producing cars. While the jury is still out on whether the latter is a good idea, in many respects. It is a matter of economics.
Binary relation extraction methods have been widely studied in recent years. However, few methods have been developed for higher n-ary relation extraction. One limiting factor is the effort required to generate training data. For binary relations, one only has to provide a few dozen pairs of entities per relation, as training data. For ternary relations (n=3), each training instance is a triplet of entities, placing a greater cognitive load on people. For example, many people know that Google acquired Youtube but not the dollar amount or the date of the acquisition and many people know that Hillary Clinton is married to Bill Clinton by not the location or date of their wedding. This makes higher n-nary training data generation a time consuming exercise in searching the Web. We present a resource for training ternary relation extractors. This was generated using a minimally supervised yet effective approach. We present statistics on the size and the quality of the dataset.
The ability to measure similarity between documents enables intelligent summarization and analysis of large corpora. Past distances between documents suffer from either an inability to incorporate semantic similarities between words or from scalability issues. As an alternative, we introduce hierarchical optimal transport as a meta-distance between documents, where documents are modeled as distributions over topics, which themselves are modeled as distributions over words. We then solve an optimal transport problem on the smaller topic space to compute a similarity score. We give conditions on the topics under which this construction defines a distance, and we relate it to the word mover's distance. We evaluate our technique for $k$-NN classification and show better interpretability and scalability with comparable performance to current methods at a fraction of the cost.
Obtaining training data for Question Answering (QA) is time-consuming and resource-intensive, and existing QA datasets are only available for limited domains and languages. In this work, we explore to what extent high quality training data is actually required for Extractive QA, and investigate the possibility of unsupervised Extractive QA. We approach this problem by first learning to generate context, question and answer triples in an unsupervised manner, which we then use to synthesize Extractive QA training data automatically. To generate such triples, we first sample random context paragraphs from a large corpus of documents and then random noun phrases or named entity mentions from these paragraphs as answers. Next we convert answers in context to "fill-in-the-blank" cloze questions and finally translate them into natural questions. We propose and compare various unsupervised ways to perform cloze-to-natural question translation, including training an unsupervised NMT model using non-aligned corpora of natural questions and cloze questions as well as a rule-based approach. We find that modern QA models can learn to answer human questions surprisingly well using only synthetic training data. We demonstrate that, without using the SQuAD training data at all, our approach achieves 56.4 F1 on SQuAD v1 (64.5 F1 when the answer is a Named entity mention), outperforming early supervised models.
We propose a novel method for exploiting the semantic structure of text to answer multiple-choice questions. The approach is especially suitable for domains that require reasoning over a diverse set of linguistic constructs but have limited training data. To address these challenges, we present the first system, to the best of our knowledge, that reasons over a wide range of semantic abstractions of the text, which are derived using off-the-shelf, general-purpose, pre-trained natural language modules such as semantic role labelers, coreference resolvers, and dependency parsers. Representing multiple abstractions as a family of graphs, we translate question answering (QA) into a search for an optimal subgraph that satisfies certain global and local properties. This formulation generalizes several prior structured QA systems. Our system, SEMANTICILP, demonstrates strong performance on two domains simultaneously. In particular, on a collection of challenging science QA datasets, it outperforms various state-of-the-art approaches, including neural models, broad coverage information retrieval, and specialized techniques using structured knowledge bases, by 2%-6%.