Related papers: Jointly Learning Sentence Embeddings and Syntax wi…
We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition…
Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching.…
Recurrent Neural Networks (RNN) have obtained excellent result in many natural language processing (NLP) tasks. However, understanding and interpreting the source of this success remains a challenge. In this paper, we propose Recurrent…
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,…
The need for tree structure modelling on top of sequence modelling is an open issue in neural dependency parsing. We investigate the impact of adding a tree layer on top of a sequential model by recursively composing subtree representations…
Incorporating stronger syntactic biases into neural language models (LMs) is a long-standing goal, but research in this area often focuses on modeling English text, where constituent treebanks are readily available. Extending constituent…
Discourse structure is integral to understanding a text and is helpful in many NLP tasks. Learning latent representations of discourse is an attractive alternative to acquiring expensive labeled discourse data. Liu and Lapata (2018) propose…
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…
Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However,…
We propose a tree-based algorithm for classification and regression problems in the context of functional data analysis, which allows to leverage representation learning and multiple splitting rules at the node level, reducing…
Contextualized representations from a pre-trained language model are central to achieve a high performance on downstream NLP task. The pre-trained BERT and A Lite BERT (ALBERT) models can be fine-tuned to give state-ofthe-art results in…
Multi-view learning can provide self-supervision when different views are available of the same data. The distributional hypothesis provides another form of useful self-supervision from adjacent sentences which are plentiful in large…
As alignment links are not given between English sentences and Abstract Meaning Representation (AMR) graphs in the AMR annotation, automatic alignment becomes indispensable for training an AMR parser. Previous studies formalize it as a…
In real practice, questions are typically complex and knowledge-intensive, requiring Large Language Models (LLMs) to recognize the multifaceted nature of the question and reason across multiple information sources. Iterative and adaptive…
In natural languages, words are used in association to construct sentences. It is not words in isolation, but the appropriate combination of hierarchical structures that conveys the meaning of the whole sentence. Neural networks can capture…
In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach…
We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model with long short-term memory recurrent neural networks…
Dependency tree structures capture long-distance and syntactic relationships between words in a sentence. The syntactic relations (e.g., nominal subject, object) can potentially infer the existence of certain named entities. In addition,…
We propose a novel architecture for Graph Neural Networks that is inspired by the idea behind Tree Kernels of measuring similarity between trees by taking into account their common substructures, named fragments. By imposing a series of…
Conversational speech, while being unstructured at an utterance level, typically has a macro topic which provides larger context spanning multiple utterances. The current language models in speech recognition systems using recurrent neural…