Success Rate

EBMT (Example-Based Machine Translation) is proposed. EBMT retrieves similar examples (pairs of source phrases, sentences, or texts and their translations) from a d~t.hase of examples, adapting the examples to translate …...

Relating the intonational characteristics of an utter- ance to other features inferable from its text is impor- tant both for speech recognition and for speech syn- thesis. This work investigates …...

Determining the relationship between the intona- tional characteristics of an utterance and other features inferable from its text is important both for speech recognition and for speech synthesis. This work …...

Keh-Jiann Chen Shing-lluan Liu Institute of lnfl~rmation Science Academia Sinica Chinese sentences are composed with string of characters without blanks to mark words. However the basic unit for sentence parsing …...

This paper addresses the alignment issue in the framework of exploitation of large bi- multilingual corpora for translation purposes. A generic alignment scheme is proposed that can meet varying requirements …...

Interactive spoken dialog provides many new challenges for spoken language systems. One of the most critical is the prevalence of speech repairs. This paper presents an al- gorithm that detects …...

AbstractWe describe the automatic resolution of pronominal anaphora using KANT Controlled English (KCE) and the KANTOO English-to-Spanish MT system. Our algorithm is based on a robust, syntax-based approach that applies …...

Answer Validation is an emerging topic in Question Answering, where open do- main systems are often required to rank huge amounts of candidate answers. We present a novel approach to …...

This paper presents a machine learning approach to bare sluice disambiguation in dialogue. We ex- tract a set of heuristic principles from a corpus-based sample and formulate them as probabilistic …...

AbstractIn this paper, we present the automatic annotation of bibliographical references’ zone in papers and articles of XML/TEI format. Our work is applied through two phases: first, we use machine …...

AbstractThis paper presents a new approach that extends Deep Dyna-Q (DDQ) by incorporating a Budget-Conscious Scheduling (BCS) to best utilize a fixed, small amount of user interactions (budget) for learning …...

AbstractGoal-Oriented Chatbots in fields such as customer support, providing certain information or general help with bookings or reservations, suffer from low performance partly due to the difficulty of obtaining large …...

AbstractWe tackle the problem of generating a pun sentence given a pair of homophones (e.g., “died” and “dyed”). Puns are by their very nature statistically anomalous and not amenable to …...

AbstractIn order to improve the sample-efficiency of deep reinforcement learning (DRL), we implemented imagination augmented agent (I2A) in spoken dialogue systems (SDS). Although I2A achieves a higher success rate than …...

AbstractThe goal-oriented dialogue system needs to be optimized for tracking the dialogue flow and carrying out an effective conversation under various situations to meet the user goal. The traditional approach …...

AbstractInterpreting how persuasive language influences audiences has implications across many domains like advertising, argumentation, and propaganda. Persuasion relies on more than a message’s content. Arranging the order of the message …...

AbstractExisting black box search methods have achieved high success rate in generating adversarial attacks against NLP models. However, such search methods are inefficient as they do not consider the amount …...

AbstractTraining dialogue agents requires a large number of interactions with users: agents have no idea about which responses are bad among a lengthy dialogue. In this paper, we propose loop-clipping …...

AbstractRecently more attention has been given to adversarial attacks on neural networks for natural language processing (NLP). A central research topic has been the investigation of search algorithms and search …...

AbstractPretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language …...

AbstractUsing natural language as a hint can supply an additional reward for playing sparse-reward games. Achieving a goal should involve several different hints, while the given hints are usually incomplete. …...

AbstractTo improve computer-based recognition from video of isolated signs from American Sign Language (ASL), we propose a new skeleton-based method that involves explicit detection of the start and end frames …...

AbstractWe propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed …...

AbstractPrevious work on pun generation commonly begins with a given pun word (a pair of homophones for heterographic pun generation and a polyseme for homographic pun generation) and seeks to …...

AbstractWe present a framework for learning hierarchical policies from demonstrations, using sparse natural language annotations to guide the discovery of reusable skills for autonomous decision-making. We formulate a generative model …...

AbstractReinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues. However, the user simulator provided by state-of-the-art dialogue frameworks are only rough approximations of human behaviour. The …...