Skip to search formSkip to main contentSkip to account menu

Text Processing Like Humans Do: Visually Attacking and Shielding NLP Systems

This work investigates the impact of visual adversarial attacks on current NLP systems on character-, word-, and sentence-level tasks, showing that both neural and non-neural models are, in contrast to humans, extremely sensitive to such attacks, suffering performance decreases of up to 82%.
View on ACL (opens in a new tab)

Dialogue Coherence Assessment Without Explicit Dialogue Act Labels

This work uses dialogue act prediction as an auxiliary task in a multi-task learning scenario to obtain informative utterance representations for coherence assessment, and alleviates the need for explicit dialogue act labels during evaluation.
View on ACL (opens in a new tab)

Generating Coherent Summaries of Scientific Articles Using Coherence Patterns

This work introduces a graph-based approach to summarize scientific articles using coherence patterns in a corpus of abstracts and proposes a method to combine coherence, importance and non-redundancy to generate the summary.
View on ACL (opens in a new tab)

A Neural Local Coherence Model for Text Quality Assessment

We propose a local coherence model that captures the flow of what semantically connects adjacent sentences in a text. We represent the semantics of a sentence by a vector and capture its state at…
View on ACL (opens in a new tab)

Graph-based Coherence Modeling For Assessing Readability

Novel graph-based coherence features based on frequent subgraphs are introduced and they outperform Pitler and Nenkova (2008) in the readability ranking task by more than 5% accuracy thus establishing a new state-of-the-art on this dataset.
View on ACL (opens in a new tab)

Lexical Coherence Graph Modeling Using Word Embeddings

The lexical coherence graph (LCG), a new graph-based model to represent lexical relations among sentences, is introduced and Kneser-Ney smoothing is adapted to smooth subgraphs’ frequencies, which improves performance.
View on ACL (opens in a new tab)

Reward Learning for Efficient Reinforcement Learning in Extractive Document Summarisation

RELIS is proposed, a novel RL paradigm that learns a reward function with Learning-to-Rank (L2R) algorithms at training time and uses this reward function to train an input-specific RL policy at test time and it is proved that RELIS guarantees to generate near-optimal summaries with appropriate L2R and RL algorithms.
View PDF on arXiv (opens in a new tab)

Improving Factual Consistency Between a Response and Persona Facts

This work proposes to fine-tune neural models for response generation by reinforcement learning and an efficient reward function that explicitly captures the consistency between a response and persona facts as well as semantic plausibility.
View on ACL (opens in a new tab)

A Neural Graph-based Local Coherence Model

This work defines a new, efficient, and effective baseline for local coherence modeling, and evaluates the neural graph-based model for two benchmark coherence evaluation tasks: sentence ordering and summary coherence rating.
View PDF (opens in a new tab)

Generating Persona-Consistent Dialogue Responses Using Deep Reinforcement Learning

This work proposes a novel approach to train transformer-based dialogue agents using actor-critic reinforcement learning, and defines a new reward function to assess generated responses in terms of persona consistency, topic consistency, and fluency.
View PDF on arXiv (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)