Related papers: Consistent CCG Parsing over Multiple Sentences for…

We present a new Convolutional Neural Network (CNN) model for text classification that jointly exploits labels on documents and their component sentences. Specifically, we consider scenarios in which annotators explicitly mark sentences (or…

Automatic segmentation of text into minimal content-bearing units is an unsolved problem even for languages like English. Spaces between words offer an easy first approximation, but this approximation is not good enough for machine…

Lexically constrained sentence generation allows the incorporation of prior knowledge such as lexical constraints into the output. This technique has been applied to machine translation, and dialog response generation. Previous work usually…

Retrieval-Augmented Generation (RAG) grounds Large Language Models (LLMs) in external knowledge but often suffers from flat context representations and stateless retrieval, leading to unstable performance. We propose Stateful…

Machine reading comprehension (MRC) poses new challenges over logical reasoning, which aims to understand the implicit logical relations entailed in the given contexts and perform inference over them. Due to the complexity of logic, logical…

End-to-end multilingual speech recognition models handle multiple languages through a single model, often incorporating language identification to automatically detect the language of incoming speech. Since the common scenario is where the…

Matching Logic is a framework for specifying programming language semantics and reasoning about programs. Its formulas are called patterns and are built with variables, symbols, connectives and quantifiers. A pattern is a combination of…

Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into…

Humans use natural language to compose common concepts from their environment into plausible, day-to-day scene descriptions. However, such generative commonsense reasoning (GCSR) skills are lacking in state-of-the-art text generation…

We describe an implemented system for robust domain-independent syntactic parsing of English, using a unification-based grammar of part-of-speech and punctuation labels coupled with a probabilistic LR parser. We present evaluations of the…

Retrieval-Augmented Generation (RAG) helps large language models (LLMs) answer knowledge-intensive and time-sensitive questions by conditioning generation on external evidence. However, most RAG systems still retrieve unstructured chunks…

Despite the broad application of deep reinforcement learning (RL), transferring and adapting the policy to unseen but similar environments is still a significant challenge. Recently, the language-conditioned policy is proposed to facilitate…

A common recent approach to semantic parsing augments sequence-to-sequence models by retrieving and appending a set of training samples, called exemplars. The effectiveness of this recipe is limited by the ability to retrieve informative…

Traditional comparative learning sentence embedding directly uses the encoder to extract sentence features, and then passes in the comparative loss function for learning. However, this method pays too much attention to the sentence body and…

Knowledge Graph Completion (KGC) aims to infer missing information in Knowledge Graphs (KGs) to address their inherent incompleteness. Traditional structure-based KGC methods, while effective, face significant computational demands and…

Sentence order prediction is the task of finding the correct order of sentences in a randomly ordered document. Correctly ordering the sentences requires an understanding of coherence with respect to the chronological sequence of events…

Recognition of handwritten words continues to be an important problem in document analysis and recognition. Existing approaches extract hand-engineered features from word images--which can perform poorly with new data sets. Recently, deep…

A major challenge in structured prediction is to represent the interdependencies within output structures. When outputs are structured as sequences, linear-chain conditional random fields (CRFs) are a widely used model class which can learn…

Distributed representations of sentences have become ubiquitous in natural language processing tasks. In this paper, we consider a continual learning scenario for sentence representations: Given a sequence of corpora, we aim to optimize the…

Determining semantic textual similarity is a core research subject in natural language processing. Since vector-based models for sentence representation often use shallow information, capturing accurate semantics is difficult. By contrast,…