相关论文: Identifying a Circuit for Verb Conjugation in GPT-…

Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A spoken language understanding system that learns from…

Research in mechanistic interpretability seeks to explain behaviors of machine learning models in terms of their internal components. However, most previous work either focuses on simple behaviors in small models, or describes complicated…

To improve the generalization of the representations for natural language processing tasks, words are commonly represented using vectors, where distances among the vectors are related to the similarity of the words. While word2vec, the…

Large-scale conversational assistants like Alexa, Siri, Cortana and Google Assistant process every utterance using multiple models for domain, intent and named entity recognition. Given the decoupled nature of model development and large…

Language models (LMs) pre-trained on massive amounts of text, in particular bidirectional encoder representations from Transformers (BERT), generative pre-training (GPT), and GPT-2, have become a key technology for many natural language…

Research suggests that providing specific and timely feedback to human tutors enhances their performance. However, it presents challenges due to the time-consuming nature of assessing tutor performance by human evaluators. Large language…

Eric Brill has recently proposed a simple and powerful corpus-based language modeling approach that can be applied to various tasks including part-of-speech tagging and building phrase structure trees. The method learns a series of symbolic…

This paper studies the potential of identifying lexical paraphrases within a single corpus, focusing on the extraction of verb paraphrases. Most previous approaches detect individual paraphrase instances within a pair (or set) of comparable…

Recent advances in NLP have been attributed to the emergence of large-scale pre-trained language models. GPT-2, in particular, is suited for generation tasks given its left-to-right language modeling objective, yet the linguistic quality of…

Pre-trained neural networks are commonly used and reused in the machine learning community. Alice trains a model for a particular task, and a part of her neural network is reused by Bob for a different task, often to great effect. To what…

Prompting and in-context learning (ICL) have become efficient learning paradigms for large language models (LLMs). However, LLMs suffer from prompt brittleness and various bias factors in the prompt, including but not limited to the…

Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing…

We argue that semantic meanings of a sentence or clause can not be interpreted independently from the rest of a paragraph, or independently from all discourse relations and the overall paragraph-level discourse structure. With the goal of…

Through specific experiences, humans learn relationships underlying the structure of events in the world. Schema theory suggests that we organize this information in mental frameworks called "schemata," which represent our knowledge of the…

Implicit discourse relation recognition is a challenging task in discourse analysis due to the absence of explicit discourse connectives between spans of text. Recent pre-trained language models have achieved great success on this task.…

Image Captioning is a fundamental task to join vision and language, concerning about cross-modal understanding and text generation. Recent years witness the emerging attention on image captioning. Most of existing works follow a traditional…

Transformer-based language models have shown an excellent ability to effectively capture and utilize contextual information. Although various analysis techniques have been used to quantify and trace the contribution of single contextual…

By far the most fruitful technique for showing lower bounds for the CONGEST model is reductions to two-party communication complexity. This technique has yielded nearly tight results for various fundamental problems such as distance…

Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can substantially improve performance on complex reasoning tasks. At the same time, In-Context Learning (ICL) has become an important mechanism…

Word2Vec is a prominent model for natural language processing (NLP) tasks. Similar inspiration is found in distributed embeddings for new state-of-the-art (SotA) deep neural networks. However, wrong combination of hyper-parameters can…