Related papers: Tactical Generation in a Free Constituent Order La…
Constructing artificial lexicons that are pronounceable, typologically plausible, and semantically structured remains an open challenge in computational linguistics. Existing conlang generators either lack formal phonotactic guarantees or…
Text generation rarely considers the control of lexical complexity, which limits its more comprehensive practical application. We introduce a novel task of lexical complexity controlled sentence generation, which aims at keywords to…
Recently, Zhang et al. (2022) propose a syntax-aware grammatical error correction (GEC) approach, named SynGEC, showing that incorporating tailored dependency-based syntax of the input sentence is quite beneficial to GEC. This work…
As generative models become ubiquitous, there is a critical need for fine-grained control over the generation process. Yet, while controlled generation methods from prompting to fine-tuning proliferate, a fundamental question remains…
One of the biggest challenges in the development and deployment of spoken dialogue systems is the design of the spoken language generation module. This challenge arises from the need for the generator to adapt to many features of the…
Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation. However, training non-monotonic models brings a new complication: how to search for a good ordering when…
A multi-turn dialogue always follows a specific topic thread, and topic shift at the discourse level occurs naturally as the conversation progresses, necessitating the model's ability to capture different topics and generate topic-aware…
To simultaneously capture syntax and global semantics from a text corpus, we propose a new larger-context recurrent neural network (RNN) based language model, which extracts recurrent hierarchical semantic structure via a dynamic deep topic…
Previous approaches to turn-taking and response generation in conversational systems have treated it as a two-stage process: First, the end of a turn is detected (based on conversation history), then the system generates an appropriate…
Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes representations, and why these representations support complex behavior remains incomplete. We…
Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step. One practical…
We introduce a framework for Thompson sampling (TS) contextual bandit algorithms, in which the algorithm's ability to quantify uncertainty and make decisions depends on the quality of a generative model that is learned offline. Instead of…
Task-oriented dialogue systems help users accomplish tasks such as booking a movie ticket and ordering food via conversation. Generative models parameterized by a deep neural network are widely used for next turn response generation in such…
We present open domain response generation with meta-words. A meta-word is a structured record that describes various attributes of a response, and thus allows us to explicitly model the one-to-many relationship within open domain dialogues…
Natural language generation provides designers with methods for automatically generating text, e.g. for creating summaries, chatbots and game content. In practise, text generators are often either learned and hard to interpret, or created…
Controlled table-to-text generation seeks to generate natural language descriptions for highlighted subparts of a table. Previous SOTA systems still employ a sequence-to-sequence generation method, which merely captures the table as a…
The sequential structure of language, and the order of words in a sentence specifically, plays a central role in human language processing. Consequently, in designing computational models of language, the de facto approach is to present…
Data-to-text generation involves transforming structured data, often represented as predicate-argument tuples, into coherent textual descriptions. Despite recent advances, systems still struggle when confronted with unseen combinations of…
In this paper, we propose a robot oriented knowledge management system based on the use of the Prolog language. Our framework hinges on a special organisation of knowledge base that enables: 1. its efficient population from natural language…
We present AGGGEN (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence…