Added: Mickelle Bien - Date: 19.12.2021 13:08 - Views: 40732 - Clicks: 8292
Thapliyal Radu Soricut. Wong Lidia S. Smith Eran Yahav. Nikolov Yuhuang Hu Richard H. Smith James Pennebaker. Paul Jordan Boyd-Graber. Hamilton Joelle Pineau. Wang Tao Lei Yoav Artzi. Nguyen Katrin Kirchhoff. Smith Omer Levy. Thomas McCoy. Alon Jacovi Yoav Goldberg. Meyer Iryna Gurevych. Kenneth Joseph Jonathan Morgan. Cohen Mirella Lapata. An analysis methodology and a case study in negation scope Yiyun Zhao Steven Bethard.
Human language acquisition research indicates that child-directed speech helps language learners. This study explores the effect of child-directed speech when learning to extract semantic information from speech directly. We find indications that CDS helps in the initial stages of learning, but eventually, models trained on reach comparable task performance, and generalize better. The suggest that this is at least partially due to linguistic rather than acoustic properties of the two registers, as we see the same pattern when looking at models trained on acoustically comparable synthetic speech.
Accurately diagnosing depression is difficult— requiring time-intensive interviews, assessments, and analysis. Hence, automated methods that can assess linguistic patterns in these interviews could help psychiatric professionals make faster, more informed decisions about diagnosis. We propose JLPC, a model that analyzes interview transcripts to identify depression while tly categorizing interview prompts into latent. This latent categorization allows the model to define high-level conversational contexts that influence patterns of language in depressed individuals.
We show that the proposed model not only outperforms competitive baselines, but that its latent prompt provide psycholinguistic insights about depression. As an essential task in task-oriented dialog systems, slot filling requires extensive training data in a certain domain. However, such data are not always available. Hence, cross-domain slot filling has naturally arisen to cope with this data scarcity problem. In this paper, we propose a Coarse-to-fine approach Coach for cross-domain slot filling.
Our model first learns the general pattern of slot entities by detecting whether the tokens are slot entities or not. It then predicts the specific types for the slot entities. In addition, we propose a template regularization approach to improve the adaptation robustness by regularizing the representation of utterances based on utterance templates.
Experimental show that our model ificantly outperforms state-of-the-art approaches in slot filling. Furthermore, our model can also be applied to the cross-domain named entity recognition task, and it achieves better adaptation performance than other existing baselines. Automatic dialogue response evaluator has been proposed as an alternative to automated metrics and human evaluation. However, existing automatic evaluators achieve only moderate correlation with human judgement and they are not robust. In this work, we propose to build a reference-free evaluator and exploit the power of semi-supervised training and pretrained masked language models.
Recent proposed approaches have made promising progress in dialogue state tracking DST. However, in multi-domain scenarios, ellipsis and reference are frequently adopted by users to express values that have been mentioned by slots from other domains.
Given a target slot, the slot connecting mechanism in DST-SC can infer its source slot and copy the source slot value directly, thus ificantly reducing the difficulty of learning and reasoning. Experimental verify the benefits of explicit slot connection modeling, and our model achieves state-of-the-art performance on MultiWOZ 2. Knowledge-driven conversation approaches have achieved remarkable research attention recently. However, generating an informative response with multiple relevant knowledge without losing fluency and coherence is still one of the main challenges.
To address this issue, this paper proposes a method that uses recurrent knowledge interaction among response decoding steps to incorporate appropriate knowledge. Furthermore, we introduce a knowledge copy mechanism using a knowledge-aware pointer network to copy words from external knowledge according to knowledge attention distribution. Our t neural conversation model which integrates recurrent Knowledge-Interaction and knowledge Copy KIC performs well on generating informative responses. Leveraging persona information of users in Neural Response Generators NRG to perform personalized conversations has been considered as an attractive and important topic in the research of conversational agents over the past few years.
Despite of the promising progress achieved by recent studies in this field, persona information tends to be incorporated into neural networks in the form of user embeddings, with the expectation that the persona can be involved via End-to-End learning. This paper proposes to adopt the personality-related characteristics of human conversations into variational response generators, by deing a specific conditional variational autoencoder based deep model with two new regularization terms employed to the loss function, so as to guide the optimization towards the direction of generating both persona-aware and relevant responses.
Besides, to reasonably evaluate the performances of various persona modeling approaches, this paper further presents three direct persona-oriented metrics from different perspectives. The experimental have shown that our proposed methodology can notably improve the performance of persona-aware response generation, and the metrics are reasonable to evaluate the.
Non-goal oriented dialog agents i. We introduce an accompanying data collection procedure to obtain We demonstrate that scaling model sizes from M to 8. We find that conditionally modeling past conversations improves perplexity by 0. Through human trials we identify positive trends between conditional modeling and style matching and outline steps to further improve persona control.
Pre-training models have been proved effective for a wide range of natural language processing tasks. Inspired by this, we propose a novel dialogue generation pre-training framework to support various kinds of conversations, including chit-chat, knowledge grounded dialogues, and conversational question answering.
In this framework, we adopt flexible attention mechanisms to fully leverage the bi-directional context and the uni-directional characteristic of language generation. We also introduce discrete latent variables to tackle the inherent one-to-many mapping problem in response generation. Two reciprocal tasks of response generation and latent act recognition are deed and carried out simultaneously within a shared network. Comprehensive experiments on three publicly available datasets verify the effectiveness and superiority of the proposed framework.
Data-driven approaches using neural networks have achieved promising performances in natural language generation NLG. However, neural generators are prone to make mistakes, e. Prior works refer this to hallucination phenomenon. In this paper, we study slot consistency for building reliable NLG systems with all slot values of input dialogue act DA properly generated in output sentences. It applies a bootstrapping algorithm to sample training candidates and uses reinforcement learning to incorporate discrete reward related to slot inconsistency into training.
Comprehensive studies have been conducted on multiple benchmark datasets, showing that the proposed methods have ificantly reduced the slot error rate ERR for all strong baselines. Human evaluations also have confirmed its effectiveness. We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task. This formulation allows for a simple integration of conversational knowledge coded in large pretrained conversational models such as ConveRT Henderson et al.
We show that leveraging such knowledge in Span-ConveRT is especially useful for few-shot learning scenarios: we report consistent gains over 1 a span extractor that trains representations from scratch in the target domain, and 2 a BERT-based span extractor. Zero-shot transfer learning for multi-domain dialogue state tracking can allow us to handle new domains without incurring the high cost of data acquisition. This paper proposes new zero-short transfer learning technique for dialogue state tracking where the in-domain training data are all synthesized from an abstract dialogue model and the ontology of the domain.
This work proposes a standalone, complete Chinese discourse parser for practical applications. We approach Chinese discourse parsing from a variety of aspects and improve the shift-reduce parser not only by integrating the pre-trained text encoder, but also by employing novel training strategies. We revise the dynamic-oracle procedure for training the shift-reduce parser, and apply unsupervised data augmentation to enhance rhetorical relation recognition. Experimental show that our Chinese discourse parser achieves the state-of-the-art performance.
Implicit discourse relation recognition is a challenging task due to the lack of connectives as strong linguistic clues. methods primarily encode two arguments separately or extract the specific interaction patterns for the task, which have not fully exploited the annotated relation al. Therefore, we propose a novel TransS-driven t learning architecture to address the issues. Specifically, based on the multi-level encoder, we 1 translate discourse relations in low-dimensional embedding space called TransSwhich could mine the latent geometric structure information of argument-relation instances; 2 further exploit the semantic features of arguments to assist discourse understanding; 3 tly learn 1 and 2 to mutually reinforce each other to obtain the better argument representations, so as to improve the performance of the task.
Extensive experimental on the Penn Discourse TreeBank PDTB show that our model achieves competitive against several state-of-the-art systems. Non-autoregressive NAR models generate all the tokens of a sequence in parallel, resulting in faster generation speed compared to their autoregressive AR counterparts but at the cost of lower accuracy. Different techniques including knowledge distillation and source-target alignment have been proposed to bridge the gap between AR and NAR models in various tasks such as neural machine translation NMTautomatic speech recognition ASRand text to speech TTS.
With the help of those techniques, NAR models can catch up with the accuracy of AR models in some tasks but not in some others. In this work, we conduct a study to understand the difficulty of NAR sequence generation and try to answer: 1 Why NAR models can catch up with AR models in some tasks but not all?
Since the main difference between AR and NAR models is that NAR models do not use dependency among target tokens while AR models do, intuitively the difficulty of NAR sequence generation heavily depends on the strongness of dependency among target tokens. To quantify such dependency, we propose an analysis model called CoMMA to characterize the difficulty of different NAR sequence generation tasks. Cross-modal language generation tasks such as image captioning are directly hurt in their ability to support non-English languages by the trend of data-hungry models combined with the lack of non-English annotations.
We investigate potential solutions for combining existing language-generation annotations in English with translation capabilities in order to create solutions at web-scale in both domain and language coverage. We describe an approach called Pivot-Language Generation Stabilization PLuGSwhich leverages directly at training time both existing English annotations gold data as well as their machine-translated versions silver data ; at run-time, it generates first an English caption and then a corresponding target-language caption. We show that PLuGS models outperform other candidate solutions in evaluations performed over 5 different target languages, under a large-domain testset using images from the Open Images dataset.
Furthermore, we find an interesting effect where the English captions generated by the PLuGS models are better than the captions generated by the original, monolingual English model. We propose a novel text editing task, referred to as fact-based text editingin which the goal is to revise a given document to better describe the facts in a knowledge base e. The task is important in practice because reflecting the truth is a common requirement in text editing.
First, we propose a method for automatically generating a dataset for research on fact-based text editing, where each instance consists of a draft text, a revised text, and several facts represented in triples. We apply the method into two public table-to-text datasets, obtaining two new datasets consisting of k and 37k instances, respectively.Free naughty chat Tang-e Eram
email: [email protected] - phone:(141) 162-5129 x 8638
Free naughty chat tang e eram