Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

"Text": models, code, and papers

INFOTABS: Inference on Tables as Semi-structured Data

May 13, 2020
Vivek Gupta, Maitrey Mehta, Pegah Nokhiz, Vivek Srikumar

In this paper, we observe that semi-structured tabulated text is ubiquitous; understanding them requires not only comprehending the meaning of text fragments, but also implicit relationships between them. We argue that such data can prove as a testing ground for understanding how we reason about information. To study this, we introduce a new dataset called INFOTABS, comprising of human-written textual hypotheses based on premises that are tables extracted from Wikipedia info-boxes. Our analysis shows that the semi-structured, multi-domain and heterogeneous nature of the premises admits complex, multi-faceted reasoning. Experiments reveal that, while human annotators agree on the relationships between a table-hypothesis pair, several standard modeling strategies are unsuccessful at the task, suggesting that reasoning about tables can pose a difficult modeling challenge.

* 16 pages, 6 figures, 14 Tables, ACL 2020, Project Page: 

  Access Paper or Ask Questions

Posterior Control of Blackbox Generation

May 10, 2020
Xiang Lisa Li, Alexander M. Rush

Text generation often requires high-precision output that obeys task-specific rules. This fine-grained control is difficult to enforce with off-the-shelf deep learning models. In this work, we consider augmenting neural generation models with discrete control states learned through a structured latent-variable approach. Under this formulation, task-specific knowledge can be encoded through a range of rich, posterior constraints that are effectively trained into the model. This approach allows users to ground internal model decisions based on prior knowledge, without sacrificing the representational power of neural generative models. Experiments consider applications of this approach for text generation. We find that this method improves over standard benchmarks, while also providing fine-grained control.

* Accepted for publication at ACL 2020 

  Access Paper or Ask Questions

FragNet: Writer Identification using Deep Fragment Networks

Mar 24, 2020
Sheng He, Lambert Schomaker

Writer identification based on a small amount of text is a challenging problem. In this paper, we propose a new benchmark study for writer identification based on word or text block images which approximately contain one word. In order to extract powerful features on these word images, a deep neural network, named FragNet, is proposed. The FragNet has two pathways: feature pyramid which is used to extract feature maps and fragment pathway which is trained to predict the writer identity based on fragments extracted from the input image and the feature maps on the feature pyramid. We conduct experiments on four benchmark datasets, which show that our proposed method can generate efficient and robust deep representations for writer identification based on both word and page images.

* IEEE Trans. on Information Forensic and Security, 2020 

  Access Paper or Ask Questions

Elephant in the Room: An Evaluation Framework for Assessing Adversarial Examples in NLP

Jan 22, 2020
Ying Xu, Xu Zhong, Antonio Jose Jimeno Yepes, Jey Han Lau

An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify. While there are a number of methods proposed to generate adversarial examples for text data, it is not trivial to assess the quality of these adversarial examples, as minor perturbations (such as changing a word in a sentence) can lead to a significant shift in their meaning, readability and classification label. In this paper, we propose an evaluation framework to assess the quality of adversarial examples based on the aforementioned properties. We experiment with five benchmark attacking methods and an alternative approach based on an auto-encoder, and found that these methods generate adversarial examples with poor readability and content preservation. We also learned that there are multiple factors that can influence the attacking performance, such as the the length of text examples and the input domain.

  Access Paper or Ask Questions

Analysis of Automatic Annotation Suggestions for Hard Discourse-Level Tasks in Expert Domains

Jun 06, 2019
Claudia Schulz, Christian M. Meyer, Jan Kiesewetter, Michael Sailer, Elisabeth Bauer, Martin R. Fischer, Frank Fischer, Iryna Gurevych

Many complex discourse-level tasks can aid domain experts in their work but require costly expert annotations for data creation. To speed up and ease annotations, we investigate the viability of automatically generated annotation suggestions for such tasks. As an example, we choose a task that is particularly hard for both humans and machines: the segmentation and classification of epistemic activities in diagnostic reasoning texts. We create and publish a new dataset covering two domains and carefully analyse the suggested annotations. We find that suggestions have positive effects on annotation speed and performance, while not introducing noteworthy biases. Envisioning suggestion models that improve with newly annotated texts, we contrast methods for continuous model adjustment and suggest the most effective setup for suggestions in future expert tasks.

* To appear in Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL 2019) 

  Access Paper or Ask Questions

Empowering Elasticsearch with Exact and Fast $r$-Neighbor Search in Hamming Space

Feb 20, 2019
Cun Mu, Jun Zhao, Guang Yang, Binwei Yang, Zheng Yan

A growing interest has been witnessed recently in building nearest neighbor search solutions within Elasticsearch--one of the most popular full-text search engines. In this paper, we focus specifically on Hamming space nearest neighbor search using Elasticsearch. By combining three techniques: bit operation, substring filtering and data preprocessing with permutation, we develop a novel approach called FENSHSES (Fast Exact Neighbor Search in Hamming Space on Elasticsearch), which achieves dramatic speed-ups over the existing term match baseline. This will empower Elasticsearch with the capability of fast information retrieval even when documents (e.g., texts, images and sounds) are represented with binary codes--a common practice in nowadays semantic representation learning.

  Access Paper or Ask Questions

Resolving Referring Expressions in Images With Labeled Elements

Oct 25, 2018
Nevan Wichers, Dilek Hakkani-Tur, Jindong Chen

Images may have elements containing text and a bounding box associated with them, for example, text identified via optical character recognition on a computer screen image, or a natural image with labeled objects. We present an end-to-end trainable architecture to incorporate the information from these elements and the image to segment/identify the part of the image a natural language expression is referring to. We calculate an embedding for each element and then project it onto the corresponding location (i.e., the associated bounding box) of the image feature map. We show that this architecture gives an improvement in resolving referring expressions, over only using the image, and other methods that incorporate the element information. We demonstrate experimental results on the referring expression datasets based on COCO, and on a webpage image referring expression dataset that we developed.

* Accepted into IEEE SLT Workshop 

  Access Paper or Ask Questions

RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes

Sep 04, 2018
Semih Yagcioglu, Aykut Erdem, Erkut Erdem, Nazli Ikizler-Cinbis

Understanding and reasoning about cooking recipes is a fruitful research direction towards enabling machines to interpret procedural text. In this work, we introduce RecipeQA, a dataset for multimodal comprehension of cooking recipes. It comprises of approximately 20K instructional recipes with multiple modalities such as titles, descriptions and aligned set of images. With over 36K automatically generated question-answer pairs, we design a set of comprehension and reasoning tasks that require joint understanding of images and text, capturing the temporal flow of events and making sense of procedural knowledge. Our preliminary results indicate that RecipeQA will serve as a challenging test bed and an ideal benchmark for evaluating machine comprehension systems. The data and leaderboard are available at

* EMNLP 2018 

  Access Paper or Ask Questions

Hierarchical Neural Story Generation

May 13, 2018
Angela Fan, Mike Lewis, Yann Dauphin

We explore story generation: creative systems that can build coherent and fluent passages of text about a topic. We collect a large dataset of 300K human-written stories paired with writing prompts from an online forum. Our dataset enables hierarchical story generation, where the model first generates a premise, and then transforms it into a passage of text. We gain further improvements with a novel form of model fusion that improves the relevance of the story to the prompt, and adding a new gated multi-scale self-attention mechanism to model long-range context. Experiments show large improvements over strong baselines on both automated and human evaluations. Human judges prefer stories generated by our approach to those from a strong non-hierarchical model by a factor of two to one.

  Access Paper or Ask Questions