Related papers: SETUP: Sentence-level English-To-Uniform Meaning R…
This paper presents our task-oriented dialog system UBAR which models task-oriented dialogs on a dialog session level. Specifically, UBAR is acquired by fine-tuning the large pre-trained unidirectional language model GPT-2 on the sequence…
Despite the widely successful applications, bootstrapping and fine-tuning semantic parsers are still a tedious process with challenges such as costly data annotation and privacy risks. In this paper, we suggest an alternative,…
Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in order to improve its word error rate (WER) performance. In…
Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Machine Translation…
Motivation: With the advent of Language Models using Transformers, popularized by ChatGPT, there is a renewed interest in exploring encoding procedures that numerically represent symbolic sequences at multiple scales and embedding…
This research introduces a new parsing approach, based on earlier syntactic work on context free grammar (CFG) and generalized phrase structure grammar (GPSG). The approach comprises both a new parsing algorithm and a set of syntactic rules…
We present TRANX, a transition-based neural semantic parser that maps natural language (NL) utterances into formal meaning representations (MRs). TRANX uses a transition system based on the abstract syntax description language for the…
Sentence embedding refers to a set of effective and versatile techniques for converting raw text into numerical vector representations that can be used in a wide range of natural language processing (NLP) applications. The majority of these…
This paper aims to achieve universal segmentation of arbitrary semantic level. Despite significant progress in recent years, specialist segmentation approaches are limited to specific tasks and data distribution. Retraining a new model for…
As large language models are increasingly deployed across diverse real-world applications, extending automated evaluation beyond English has become a critical challenge. Existing evaluation approaches are predominantly English-focused, and…
The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders. In this work, we explore an alternative paradigm. We formulate…
Referring expression segmentation (RES) aims at segmenting the entities' masks that match the descriptive language expression. While traditional RES methods primarily address object-level grounding, real-world scenarios demand a more…
Summarization quality evaluation is a non-trivial task in text summarization. Contemporary methods can be mainly categorized into two scenarios: (1) reference-based: evaluating with human-labeled reference summary; (2) reference-free:…
With the thriving of pre-trained language model (PLM) widely verified in various of NLP tasks, pioneer efforts attempt to explore the possible cooperation of the general textual information in PLM with the personalized behavioral…
Unified opinion role labeling (ORL) aims to detect all possible opinion structures of 'opinion-holder-target' in one shot, given a text. The existing transition-based unified method, unfortunately, is subject to longer opinion terms and…
This study addresses the issues of semantic entanglement, unclear label structure, and insufficient feature representation in few-shot text classification, and proposes an optimization framework based on structured prompts to enhance…
Most of modern neural machine translation (NMT) models are based on an encoder-decoder framework with an attention mechanism. While they perform well on standard datasets, they can have trouble in translation of long inputs that are rare or…
Generative Universal Speech Enhancement (USE) methods aim to leverage generative models to improve speech quality under various types of distortions. However, existing generative speech enhancement methods often suffer from semantic…
This paper builds on previous work using Combinatory Categorial Grammar (CCG) to derive a transparent syntax-semantics interface for Abstract Meaning Representation (AMR) parsing. We define new semantics for the CCG combinators that is…
Visual Place Recognition (VPR) in long-term deployment requires reasoning beyond pixel similarity: systems must make transparent, interpretable decisions that remain robust under lighting, weather and seasonal change. We present Text2Graph…