Related papers: Interleaving Syntax and Semantics in an Efficient …

How to best integrate linguistic and perceptual processing in multi-modal tasks that involve language and vision is an important open problem. In this work, we argue that the common practice of using language in a top-down manner, to direct…

An approximate textual retrieval algorithm for searching sources with high levels of defects is presented. It considers splitting the words in a query into two overlapping segments and subsequently building composite regular expressions…

Latent tree learning models represent sentences by composing their words according to an induced parse tree, all based on a downstream task. These models often outperform baselines which use (externally provided) syntax trees to drive the…

Computing devices have recently become capable of interacting with their end users via natural language. However, they can only operate within a limited "supported" domain of discourse and fail drastically when faced with an out-of-domain…

Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…

This paper describes the functioning of a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The paper first introduces key notions in language modeling and…

Shallow syntax provides an approximation of phrase-syntactic structure of sentences; it can be produced with high accuracy, and is computationally cheap to obtain. We investigate the role of shallow syntax-aware representations for NLP…

This paper attempts a more formal approach to the legibility of text based programming languages, presenting, with proof, minimum possible ways of representing structure in text interleaved with information. This presumes that a minimalist…

Semantic feedback is an important source of information that a parser could use to deal with local ambiguities in syntax. However, it is difficult to devise a systematic communication mechanism for interactive syntax and semantics. In this…

Both bottom-up and top-down strategies have been used for neural transition-based constituent parsing. The parsing strategies differ in terms of the order in which they recognize productions in the derivation tree, where bottom-up…

In hierarchical text classification, we perform a sequence of inference steps to predict the category of a document from top to bottom of a given class taxonomy. Most of the studies have focused on developing novels neural network…

We consider retrofitting structure-aware Transformer-based language model for facilitating end tasks by proposing to exploit syntactic distance to encode both the phrasal constituency and dependency connection into the language model. A…

This paper extends a polynomial-time parsing algorithm that resolves structural ambiguity in input to a speech-based user interface by calculating and comparing the denotations of rival constituents, given some model of the interfaced…

Improving the captioning performance on low-resource languages by leveraging English caption datasets has received increasing research interest in recent years. Existing works mainly fall into two categories: translation-based and…

Many successful approaches to semantic parsing build on top of the syntactic analysis of text, and make use of distributional representations or statistical models to match parses to ontology-specific queries. This paper presents a novel…

This thesis explores challenges in semantic parsing, specifically focusing on scenarios with limited data and computational resources. It offers solutions using techniques like automatic data curation, knowledge transfer, active learning,…

Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…

Sentence embedding tasks are important in natural language processing (NLP), but improving their performance while keeping them reliable is still hard. This paper presents a framework that combines pseudo-label generation and model ensemble…

To date, most work on text simplification has focused on sentence-level inputs. Early attempts at document simplification merely applied these approaches iteratively over the sentences of a document. However, this fails to coherently…

Traditional language processing tools constrain language designers to specific kinds of grammars. In contrast, model-based language specification decouples language design from language processing. As a consequence, model-based language…