Alert button
Picture for Archna Bhatia

Archna Bhatia

Alert button

Learning to Plan and Realize Separately for Open-Ended Dialogue Systems

Oct 04, 2020
Sashank Santhanam, Zhuo Cheng, Brodie Mather, Bonnie Dorr, Archna Bhatia, Bryanna Hebenstreit, Alan Zemel, Adam Dalton, Tomek Strzalkowski, Samira Shaikh

Figure 1 for Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
Figure 2 for Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
Figure 3 for Learning to Plan and Realize Separately for Open-Ended Dialogue Systems
Figure 4 for Learning to Plan and Realize Separately for Open-Ended Dialogue Systems

Achieving true human-like ability to conduct a conversation remains an elusive goal for open-ended dialogue systems. We posit this is because extant approaches towards natural language generation (NLG) are typically construed as end-to-end architectures that do not adequately model human generation processes. To investigate, we decouple generation into two separate phases: planning and realization. In the planning phase, we train two planners to generate plans for response utterances. The realization phase uses response plans to produce an appropriate response. Through rigorous evaluations, both automated and human, we demonstrate that decoupling the process into planning and realization performs better than an end-to-end approach.

* Accepted at EMNLP 2020 (Findings) 
Viaarxiv icon

From Spatial Relations to Spatial Configurations

Jul 19, 2020
Soham Dan, Parisa Kordjamshidi, Julia Bonn, Archna Bhatia, Jon Cai, Martha Palmer, Dan Roth

Figure 1 for From Spatial Relations to Spatial Configurations
Figure 2 for From Spatial Relations to Spatial Configurations
Figure 3 for From Spatial Relations to Spatial Configurations
Figure 4 for From Spatial Relations to Spatial Configurations

Spatial Reasoning from language is essential for natural language understanding. Supporting it requires a representation scheme that can capture spatial phenomena encountered in language as well as in images and videos. Existing spatial representations are not sufficient for describing spatial configurations used in complex tasks. This paper extends the capabilities of existing spatial representation languages and increases coverage of the semantic aspects that are needed to ground the spatial meaning of natural language text in the world. Our spatial relation language is able to represent a large, comprehensive set of spatial concepts crucial for reasoning and is designed to support the composition of static and dynamic spatial configurations. We integrate this language with the Abstract Meaning Representation(AMR) annotation schema and present a corpus annotated by this extended AMR. To exhibit the applicability of our representation scheme, we annotate text taken from diverse datasets and show how we extend the capabilities of existing spatial representation languages with the fine-grained decomposition of semantics and blend it seamlessly with AMRs of sentences and discourse representations as a whole.

* LREC 2020  
Viaarxiv icon

The Panacea Threat Intelligence and Active Defense Platform

Apr 20, 2020
Adam Dalton, Ehsan Aghaei, Ehab Al-Shaer, Archna Bhatia, Esteban Castillo, Zhuo Cheng, Sreekar Dhaduvai, Qi Duan, Md Mazharul Islam, Younes Karimi, Amir Masoumzadeh, Brodie Mather, Sashank Santhanam, Samira Shaikh, Tomek Strzalkowski, Bonnie J. Dorr

Figure 1 for The Panacea Threat Intelligence and Active Defense Platform
Figure 2 for The Panacea Threat Intelligence and Active Defense Platform

We describe Panacea, a system that supports natural language processing (NLP) components for active defenses against social engineering attacks. We deploy a pipeline of human language technology, including Ask and Framing Detection, Named Entity Recognition, Dialogue Engineering, and Stylometry. Panacea processes modern message formats through a plug-in architecture to accommodate innovative approaches for message analysis, knowledge representation and dialogue generation. The novelty of the Panacea system is that uses NLP for cyber defense and engages the attacker using bots to elicit evidence to attribute to the attacker and to waste the attacker's time and resources.

* Accepted at STOC 
Viaarxiv icon

Adaptation of a Lexical Organization for Social Engineering Detection and Response Generation

Apr 20, 2020
Archna Bhatia, Adam Dalton, Brodie Mather, Sashank Santhanam, Samira Shaikh, Alan Zemel, Tomek Strzalkowski, Bonnie J. Dorr

Figure 1 for Adaptation of a Lexical Organization for Social Engineering Detection and Response Generation
Figure 2 for Adaptation of a Lexical Organization for Social Engineering Detection and Response Generation
Figure 3 for Adaptation of a Lexical Organization for Social Engineering Detection and Response Generation

We present a paradigm for extensible lexicon development based on Lexical Conceptual Structure to support social engineering detection and response generation. We leverage the central notions of ask (elicitation of behaviors such as providing access to money) and framing (risk/reward implied by the ask). We demonstrate improvements in ask/framing detection through refinements to our lexical organization and show that response generation qualitatively improves as ask/framing detection performance improves. The paradigm presents a systematic and efficient approach to resource adaptation for improved task-specific performance.

* Accepted at STOC 
Viaarxiv icon

Detecting Asks in SE attacks: Impact of Linguistic and Structural Knowledge

Feb 25, 2020
Bonnie J. Dorr, Archna Bhatia, Adam Dalton, Brodie Mather, Bryanna Hebenstreit, Sashank Santhanam, Zhuo Cheng, Samira Shaikh, Alan Zemel, Tomek Strzalkowski

Figure 1 for Detecting Asks in SE attacks: Impact of Linguistic and Structural Knowledge
Figure 2 for Detecting Asks in SE attacks: Impact of Linguistic and Structural Knowledge
Figure 3 for Detecting Asks in SE attacks: Impact of Linguistic and Structural Knowledge
Figure 4 for Detecting Asks in SE attacks: Impact of Linguistic and Structural Knowledge

Social engineers attempt to manipulate users into undertaking actions such as downloading malware by clicking links or providing access to money or sensitive information. Natural language processing, computational sociolinguistics, and media-specific structural clues provide a means for detecting both the ask (e.g., buy gift card) and the risk/reward implied by the ask, which we call framing (e.g., lose your job, get a raise). We apply linguistic resources such as Lexical Conceptual Structure to tackle ask detection and also leverage structural clues such as links and their proximity to identified asks to improve confidence in our results. Our experiments indicate that the performance of ask detection, framing detection, and identification of the top ask is improved by linguistically motivated classes coupled with structural clues such as links. Our approach is implemented in a system that informs users about social engineering risk situations.

* Accepted at AAAI 2020 
Viaarxiv icon

Adposition and Case Supersenses v2: Guidelines for English

Jul 02, 2018
Nathan Schneider, Jena D. Hwang, Archna Bhatia, Na-Rae Han, Vivek Srikumar, Tim O'Gorman, Sarah R. Moeller, Omri Abend, Austin Blodgett, Jakob Prange

This document offers a detailed linguistic description of SNACS (Semantic Network of Adposition and Case Supersenses; Schneider et al., 2018), an inventory of 50 semantic labels ("supersenses") that characterize the use of adpositions and case markers at a somewhat coarse level of granularity, as demonstrated in the STREUSLE 4.1 corpus (https://github.com/nert-gu/streusle/). Though the SNACS inventory aspires to be universal, this document is specific to English; documentation for other languages will be published separately. Version 2 is a revision of the supersense inventory proposed for English by Schneider et al. (2015, 2016) (henceforth "v1"), which in turn was based on previous schemes. The present inventory was developed after extensive review of the v1 corpus annotations for English, plus previously unanalyzed genitive case possessives (Blodgett and Schneider, 2018), as well as consideration of adposition and case phenomena in Hebrew, Hindi, Korean, and German. Hwang et al. (2017) present the theoretical underpinnings of the v2 scheme. Schneider et al. (2018) summarize the scheme, its application to English corpus data, and an automatic disambiguation task.

Viaarxiv icon

Coping with Construals in Broad-Coverage Semantic Annotation of Adpositions

Mar 10, 2017
Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O'Gorman, Vivek Srikumar, Nathan Schneider

Figure 1 for Coping with Construals in Broad-Coverage Semantic Annotation of Adpositions

We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4,250 preposition tokens in a 55,000 word corpus of English. Attempts to apply the scheme to adpositions and case markers in other languages, as well as some problematic cases in English, have led us to reconsider the assumption that a preposition's lexical contribution is equivalent to the role/relation that it mediates. Our proposal is to embrace the potential for construal in adposition use, expressing such phenomena directly at the token level to manage complexity and avoid sense proliferation. We suggest a framework to represent both the scene role and the adposition's lexical function so they can be annotated at scale---supporting automatic, statistical processing of domain-general language---and sketch how this representation would inform a constructional analysis.

* Presentation at Construction Grammar and NLU AAAI Spring Symposium, Stanford, March 27-29 2017; 9 pages including references; 1 figure 
Viaarxiv icon