Related papers: Keeping Notes: Conditional Natural Language Genera…

Paraphrasing natural language sentences is a multifaceted process: it might involve replacing individual words or short phrases, local rearrangement of content, or high-level restructuring like topicalization or passivization. Past…

Copying mechanism shows effectiveness in sequence-to-sequence based neural network models for text generation tasks, such as abstractive sentence summarization and question generation. However, existing works on modeling copying or pointing…

We consider the problem of neural semantic parsing, which translates natural language questions into executable SQL queries. We introduce a new mechanism, execution guidance, to leverage the semantics of SQL. It detects and excludes faulty…

Natural question generation (QG) aims to generate questions from a passage and an answer. Previous works on QG either (i) ignore the rich structure information hidden in text, (ii) solely rely on cross-entropy loss that leads to issues like…

Modern Neural Machine Translation systems exhibit strong performance in several different languages and are constantly improving. Their ability to learn continuously is, however, still severely limited by the catastrophic forgetting issue.…

Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text, and absent keyphrase which does not match any contiguous subsequence…

Paraphrase generation is a longstanding NLP task that has diverse applications for downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised…

Bridging robot action sequences and their natural language captions is an important task to increase explainability of human assisting robots in their recently evolving field. In this paper, we propose a system for generating natural…

We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the…

Copy mechanisms are employed in sequence to sequence models (seq2seq) to generate reproductions of words from the input to the output. These frameworks, operating at the lexical type level, fail to provide an explicit alignment that records…

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…

Sentences produced by abstractive summarization systems can be ungrammatical and fail to preserve the original meanings, despite being locally fluent. In this paper we propose to remedy this problem by jointly generating a sentence and its…

Large pre-trained language models help to achieve state of the art on a variety of natural language processing (NLP) tasks, nevertheless, they still suffer from forgetting when incrementally learning a sequence of tasks. To alleviate this…

Curriculum learning has shown promising improvements in multiple domains by training machine learning models from easy samples to hard ones. Previous works which either design rules or train models for scoring the difficulty highly rely on…

In Natural Language Generation (NLG), End-to-End (E2E) systems trained through deep learning have recently gained a strong interest. Such deep models need a large amount of carefully annotated data to reach satisfactory performance.…

We consider incorporating topic information into the sequence-to-sequence framework to generate informative and interesting responses for chatbots. To this end, we propose a topic aware sequence-to-sequence (TA-Seq2Seq) model. The model…

Recent developments in Language Models (LMs) have shown their effectiveness in NLP tasks, particularly in knowledge-intensive tasks. However, the mechanisms underlying knowledge storage and memory access within their parameters remain…

Building effective text generation systems requires three critical components: content selection, text planning, and surface realization, and traditionally they are tackled as separate problems. Recent all-in-one style neural generation…

We model the recursive production property of context-free grammars for natural and synthetic languages. To this end, we present a dynamic programming algorithm that marginalises over latent binary tree structures with $N$ leaves, allowing…