Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks148 from public data
- A Diversity-Promoting Objective Function for Neural Conversation Models2,879
This work proposes using Maximum Mutual Information (MMI) as the objective function in neural models, and demonstrates that the proposed MMI models produce more diverse, interesting, and appropriate responses, yielding substantive gains in BLEU scores on two conversational datasets and in human evaluations.
- Deep Reinforcement Learning for Dialogue Generation1,434
This work simulates dialogues between two virtual agents, using policy gradient methods to reward sequences that display three useful conversational properties: informativity, non-repetitive turns, coherence, and ease of answering.
- A Persona-Based Neural Conversation Model1,122
This work presents persona-based models for handling the issue of speaker consistency in neural response generation that yield qualitative performance improvements in both perplexity and BLEU scores over baseline sequence-to-sequence models.
- Adversarial Learning for Neural Dialogue Generation927
This work applies adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances, and investigates models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls.
- Dice Loss for Data-imbalanced NLP Tasks796
This paper proposes to use dice loss in replacement of the standard cross-entropy objective for data-imbalanced NLP tasks, based on the Sørensen--Dice coefficient or Tversky index, which attaches similar importance to false positives and false negatives, and is more immune to the data-IMbalance issue.
- A Unified MRC Framework for Named Entity Recognition709
This paper proposes to formulate the task of NER as a machine reading comprehension (MRC) task, and naturally tackles the entity overlapping issue in nested NER: the extraction of two overlapping entities with different categories requires answering two independent questions.
- A Hierarchical Neural Autoencoder for Paragraphs and Documents618
This paper introduces an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph and evaluates the reconstructed paragraph using standard metrics to show that neural models are able to encode texts in a way that preserve syntactic, semantic, and discourse coherence.
- 444
- 399
- Entity-Relation Extraction as Multi-Turn Question Answering395
The proposed multi-turn QA model achieves the best performance on the RESUME dataset, which requires multi-step reasoning to construct entity dependencies, as opposed to the single-step dependency extraction in the triplet exaction in previous datasets.
- Towards a General Rule for Identifying Deceptive Opinion Spam386
This paper explores generalized approaches for identifying online deceptive opinion spam based on a new gold standard dataset, which is comprised of data from three different domains that contains three types of reviews, i.e. customer generated truthful reviews, Turker generated deceptive reviews and employee (domain-expert) generated deception reviews.
- BertGCN: Transductive Text Classification by Combining GNN and BERT329
BertGCN constructs a heterogeneous graph over the dataset and represents documents as nodes using BERT representations and GCN modules within BertGCN, a model that combines large scale pretraining and transductive learning for text classification.
- Text Classification via Large Language Models296
Clue And Reasoning Prompting (CARP) adopts a progressive reasoning strategy tailored to addressing the complex linguistic phenomena involved in text classification, and achieves comparable performances to supervised models with 1,024 examples per class.
- ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information244
This work proposes ChineseBERT, which incorporates both the glyph and pinyin information of Chinese characters into language model pretraining and achieves new SOTA performances on a wide range of Chinese NLP tasks, including machine reading comprehension, natural language inference, text classification, sentence pair matching, and competitive performances in named entity recognition and word segmentation.
- Do Multi-Sense Embeddings Improve Natural Language Understanding?241
A multisense embedding model based on Chinese Restaurant Processes is introduced that achieves state of the art performance on matching human word similarity judgments, and a pipelined architecture for incorporating multi-sense embeddings into language understanding is proposed.
- 224
- Glyce: Glyph-vectors for Chinese Character Representations221
Glyce, the glyph-vectors for Chinese character representations, is presented and it is shown that glyph-based models are able to consistently outperform word/char ID- based models in a wide range of Chinese NLP tasks.
- CorefQA: Coreference Resolution as Query-based Span Prediction198
CorefQA is presented, an accurate and extensible approach for the coreference resolution task, formulated as a span prediction task, like in question answering, which provides the flexibility of retrieving mentions left out at the mention proposal stage.
- Automated known problem diagnosis with event traces188
This work proposes to use system behavior information such as system event traces to build correlations with solved problems, instead of using only vague text descriptions as in existing practices to enable automatic identification of the root cause of a problem if it is a known one, which would further lead to its resolution.
- A Model of Coherence Based on Distributed Sentence Representation162
A neural network model for the coherence task based on distributed sentence representation is introduced, which outperforms existing baselines and generates the state-of-art performance in standard coherence evaluation tasks.
- Recursive Deep Models for Discourse Parsing151
This paper proposes a recursive model for discourse parsing that jointly models distributed representations for clauses, sentences, and entire discourses that obtains comparable performance regarding standard discoursing parsing evaluations when compared against current state-of-art systems.
- Is Word Segmentation Necessary for Deep Learning of Chinese Representations?141
It is shown that word-based models are more vulnerable to data sparsity and the presence of out-of-vocabulary (OOV) words, and thus more prone to overfitting, and this could encourage researchers in the community to rethink the necessity of word segmentation in deep learning-based Chinese Natural Language Processing.
- 116
- Major Life Event Extraction from Twitter based on Congratulations/Condolences Speech Acts115
The feasibility of accurately extracting major life events is demonstrated and the system extracts a fine-grained description of users’ life events based on their published tweets is optimistic that it can help Twitter users more easily grasp information from users they take interest in following and also facilitate many downstream applications, for example realtime friend recommendation.
- Triggerless Backdoor Attack for NLP Tasks with Clean Labels109
A new strategy to perform textual backdoor attack which does not require an external trigger and the poisoned samples are correctly labeled is proposed, which marks the first step towards developing triggerless attacking strategies in NLP.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.