Constrained Decoding
Related Papers
Learning Translation Boundaries for Phrase-Based Decoding
Constrained decoding is of great importance not only for speed but also for translation qual- ity. Previous efforts explore soft syntactic con- straints which are based on constituent bound- aries …...
Natural Language Model Re-usability for Scaling to Different Domains
Natural language understanding is the core of the human computer interactions. How- ever, building new domains and tasks that need a separate set of models is a bottle- neck for …...
Deep Semantic Role Labeling: What Works and What’s Next
AbstractWe introduce a new deep learning model for semantic role labeling (SRL) that significantly improves the state of the art, along with detailed analyses to reveal its strengths and limitations. …...
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue
AbstractGenerating 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, …...
Training Neural Machine Translation to Apply Terminology Constraints
AbstractThis paper proposes a novel method to inject custom terminology into neural machine translation at run time. Previous works have mainly proposed modifications to the decoding algorithm in order to …...
“Nice Try, Kiddo”: Investigating Ad Hominems in Dialogue Responses
AbstractAd hominem attacks are those that target some feature of a person’s character instead of the position the person is maintaining. These attacks are harmful because they propagate implicit biases …...
Mention Flags (MF): Constraining Transformer-based Text Generators
AbstractThis paper focuses on Seq2Seq (S2S) constrained text generation where the text generator is constrained to mention specific words which are inputs to the encoder in the generated outputs. Pre-trained …...
Neural Machine Translation with Inflected Lexicon
AbstractThe paper presents experiments in neural machine translation with lexical constraints into a morphologically rich language. In particular and we introduce a method and based on constrained decoding and which …...
Dynamic Global Memory for Document-level Argument Extraction
AbstractExtracting informative arguments of events from news articles is a challenging problem in information extraction, which requires a global contextual understanding of each document. While recent work on document-level extraction …...
PLM-based World Models for Text-based Games
AbstractWorld models have improved the ability of reinforcement learning agents to operate in a sample efficient manner, by being trained to predict plausible changes in the underlying environment. As the …...
Seq2Path: Generating Sentiment Tuples as Paths of a Tree
AbstractAspect-based sentiment analysis (ABSA) tasks aim to extract sentiment tuples from a sentence. Recent generative methods such as Seq2Seq models have achieved good performance by formulating the output as a …...
The University of Edinburgh’s Submission to the WMT22 Code-Mixing Shared Task (MixMT)
AbstractThe University of Edinburgh participated in the WMT22 shared task on code-mixed translation. This consists of two subtasks: i) generating code-mixed Hindi/English (Hinglish) text generation from parallel Hindi and English …...
TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base
AbstractPre-trained language models (PLMs) have shown their effectiveness in multiple scenarios. However, KBQA remains challenging, especially regarding coverage and generalization settings. This is due to two main factors: i) understanding …...
Zero-shot Sonnet Generation with Discourse-level Planning and Aesthetics Features
AbstractPoetry generation, and creative language generation in general, usually suffers from the lack of large training data. In this paper, we present a novel framework to generate sonnets that does …...