Related papers: Neural Text Generation from Rich Semantic Represen…

Current open-domain neural semantics parsers show impressive performance. However, closer inspection of the symbolic meaning representations they produce reveals significant weaknesses: sometimes they tend to merely copy character sequences…

Recent studies show that Generative Relevance Feedback (GRF), using text generated by Large Language Models (LLMs), can enhance the effectiveness of query expansion. However, LLMs can generate irrelevant information that harms retrieval…

Headline generation for spoken content is important since spoken content is difficult to be shown on the screen and browsed by the user. It is a special type of abstractive summarization, for which the summaries are generated word by word…

Coherence plays a critical role in producing a high-quality summary from a document. In recent years, neural extractive summarization is becoming increasingly attractive. However, most of them ignore the coherence of summaries when…

The development of next-generation molecular simulation models requires moving beyond pre-defined functional forms toward machine learning (ML) techniques that directly capture multiscale physics. Here, we demonstrate such an approach using…

Conversational Recommender Systems (CRSs) aim to provide personalized recommendations by interacting with users through conversations. Most existing studies of CRS focus on extracting user preferences from conversational contexts. However,…

This paper evaluates the utility of Rhetorical Structure Theory (RST) trees and relations in discourse coherence evaluation. We show that incorporating silver-standard RST features can increase accuracy when classifying coherence. We…

Generating from Abstract Meaning Representation (AMR) is an underspecified problem, as many syntactic decisions are not constrained by the semantic graph. To explicitly account for this underspecification, we break down generating from AMR…

Automated Text Scoring (ATS) provides a cost-effective and consistent alternative to human marking. However, in order to achieve good performance, the predictive features of the system need to be manually engineered by human experts. We…

Representative Selection (RS) is the problem of finding a small subset of exemplars from a dataset that is representative of the dataset. In this paper, we study RS for attributed graphs, and focus on finding representative nodes that…

Automatic Speech Recognition (ASR) aims to convert human speech content into corresponding text. In conversational scenarios, effectively utilizing context can enhance its accuracy. Large Language Models' (LLMs) exceptional long-context…

With an ever increasing size of text present on the Internet, automatic summary generation remains an important problem for natural language understanding. In this work we explore a novel full-fledged pipeline for text summarization with an…

We introduce a novel scheme for parsing a piece of text into its Abstract Meaning Representation (AMR): Graph Spanning based Parsing (GSP). One novel characteristic of GSP is that it constructs a parse graph incrementally in a top-down…

Despite the success of attention-based neural models for natural language generation and classification tasks, they are unable to capture the discourse structure of larger documents. We hypothesize that explicit discourse representations…

Neural dependency parsing has achieved remarkable performance for many domains and languages. The bottleneck of massive labeled data limits the effectiveness of these approaches for low resource languages. In this work, we focus on…

Attentional, RNN-based encoder-decoder models for abstractive summarization have achieved good performance on short input and output sequences. For longer documents and summaries however these models often include repetitive and incoherent…

Maximum likelihood estimation (MLE) is the predominant algorithm for training text generation models. This paradigm relies on direct supervision examples, which is not applicable to many emerging applications, such as generating adversarial…

We present a transition-based AMR parser that directly generates AMR parses from plain text. We use Stack-LSTMs to represent our parser state and make decisions greedily. In our experiments, we show that our parser achieves very competitive…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

Systems that generate natural language text from abstract meaning representations such as AMR are typically evaluated using automatic surface matching metrics that compare the generated texts to reference texts from which the input meaning…