相关论文: Measuring Alignment Bias in Neural Seq2Seq Semanti…

The problem of learning to translate between two vector spaces given a set of aligned points arises in several application areas of NLP. Current solutions assume that the lexicon which defines the alignment pairs is noise-free. We consider…

This paper provides a comprehensive analysis of the first shared task on End-to-End Natural Language Generation (NLG) and identifies avenues for future research based on the results. This shared task aimed to assess whether recent…

This paper describes Difference-aware Deep continuous prompt for Contrastive Sentence Embeddings (D2CSE) that learns sentence embeddings. Compared to state-of-the-art approaches, D2CSE computes sentence vectors that are exceptional to…

The relevance between a query and a document in search can be represented as matching degree between the two objects. Latent space models have been proven to be effective for the task, which are often trained with click-through data. One…

Consistency, which refers to the capability of generating the same predictions for semantically similar contexts, is a highly desirable property for a sound language understanding model. Although recent pretrained language models (PLMs)…

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

In reading comprehension, generating sentence-level distractors is a significant task, which requires a deep understanding of the article and question. The traditional entity-centered methods can only generate word-level or phrase-level…

Network embeddings, which learn low-dimensional representations for each vertex in a large-scale network, have received considerable attention in recent years. For a wide range of applications, vertices in a network are typically…

Despite the success of sequence-to-sequence (seq2seq) models in semantic parsing, recent work has shown that they fail in compositional generalization, i.e., the ability to generalize to new structures built of components observed during…

Due to advances in Large Language Models (LLMs) such as ChatGPT, the boundary between human-written text and AI-generated text has become blurred. Nevertheless, recent work has demonstrated that it is possible to reliably detect…

We formulate an attention mechanism for continuous and ordered sequences that explicitly functions as an alignment model, which serves as the core of many sequence-to-sequence tasks. Standard scaled dot-product attention relies on…

A sequence-to-sequence model is a neural network module for mapping two sequences of different lengths. The sequence-to-sequence model has three core modules: encoder, decoder, and attention. Attention is the bridge that connects the…

Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. Avenues like the E2E NLG Challenge have encouraged the development of neural approaches,…

We discuss the feasibility of the following learning problem: given unmatched samples from two domains and nothing else, learn a mapping between the two, which preserves semantics. Due to the lack of paired samples and without any…

Recent work on the problem of latent tree learning has made it possible to train neural networks that learn to both parse a sentence and use the resulting parse to interpret the sentence, all without exposure to ground-truth parse trees at…

Deep time series models continue to improve predictive performance, yet their deployment remains limited by their black-box nature. In response, existing interpretability approaches in the field keep focusing on explaining the internal…

This work exploits translation data as a source of semantically relevant learning signal for models of word representation. In particular, we exploit equivalence through translation as a form of distributed context and jointly learn how to…

Semantic parsing is the process of translating natural language utterances into logical forms, which has many important applications such as question answering and instruction following. Sequence-to-sequence models have been very successful…

Recently, various neural encoder-decoder models pioneered by Seq2Seq framework have been proposed to achieve the goal of generating more abstractive summaries by learning to map input text to output text. At a high level, such neural models…

Sequence generation models are increasingly being used to translate natural language into programs, i.e. to perform executable semantic parsing. The fact that semantic parsing aims to predict programs that can lead to executed actions in…