SPNLP @ EMNLP 2020

7 papers

Top Research Directions

The 23 research directions with SPNLP @ EMNLP 2020 papers, ranked by paper count, next to 2017. Share is the fraction of the edition’s papers in the direction.

#Direction20202017Share 2020Share 20172017 rank
1Adaptive Context Gating for Neural Sequence Generation1014.3%0.0%—
2Automated Rule Induction for Neuro-Symbolic AI1014.3%0.0%—
3Bridging the Form Meaning Gap via Semantic Grounding1014.3%0.0%—
4Continuous Relaxations for Learning Discrete Logic1014.3%0.0%—
5Cross-Task Generalization of Sequence Transduction Mechanisms1014.3%0.0%—
6Differentiable Approximations of Discrete Logic1014.3%0.0%—
7Document Level Evaluation Gaps in Machine Translation1014.3%0.0%—
8Generalizing Event Extraction to Unseen Categories1014.3%0.0%—
9Hard Monotonic Attention for Sequence Alignment1014.3%0.0%—
10Hierarchical Feature Abstraction Across Transformer Layers1014.3%0.0%—
11Information Extraction as Reading Comprehension1014.3%0.0%—
12Learning from Long Tailed Distributions1014.3%0.0%—
13Overcoming the Parallel Document Scarcity Bottleneck1014.3%0.0%—
14Pointer Generator Mechanisms for Grounded Text Generation1014.3%0.0%—
15Recognizing Nested and Overlapping Named Entities1014.3%0.0%—
16Stochastic Latent Spaces for Diverse Sequence Generation1014.3%0.0%—
17Syntactic Templates for Controlled Text Generation1014.3%0.0%—
18The Semantic Peak of Intermediate Transformer Layers1014.3%0.0%—
19The Symbolic Translation Bottleneck in Neuro Symbolic Reasoning1014.3%0.0%—
20The Tension Between Density Estimation and Sample Quality1014.3%0.0%—
21Truncation and Sampling Strategies for Language Model Decoding1014.3%0.0%—
22Verifying Synthetic Data via Cross-Method Consistency1014.3%0.0%—
23Visual Grounding for Semantic Disambiguation1014.3%0.0%—

Download all directions as CSV

Institutions

Institutions credited by SPNLP @ EMNLP 2020 papers: a paper credits every institution named in its affiliations, once. 9 institutions share 7 credited papers.

#InstitutionPapersShare20172017 rank
1New York University 342.9%0—
2Johns Hopkins University 228.6%0—
3Amazon (United States) 114.3%0—
4Arizona State University 114.3%0—
5Google (United States) 114.3%0—
6Meta (United States) 114.3%0—
7Microsoft (United States) 114.3%0—
8Toyota Technological Institute at Chicago 114.3%0—
9University of Rochester 114.3%0—

Download all institutions as CSV

About this data

Papers. SPNLP @ EMNLP 2020 lists 7 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2017 use shares, since the edition went from 5 to 7 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 7 of 7 papers (100.0%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-19 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “SPNLP @ EMNLP 2020”, https://lacuna.tiptreesystems.com/venue/spnlp-emnlp/2020.

Top Authors

AuthorPapers
Benjamin Van Durme2
Kyunghyun Cho2
Aaron Steven White1
Chitta Baral1
Guanghui Qin1
Ke Tran1
Lifu Tu1
Ming Tan1
Orhan Firat1
Patrick Xia1
Richard Yuanzhe Pang1
Sébastien Jean1
Seth Ebner1
Tongfei Chen1
Yunmo Chen1

Impactful Papers

Papers from SPNLP @ EMNLP 2020 that shaped research clusters.

Influential

Papers

Title
CopyNext: Explicit Span Copying and Alignment in Sequence to Sequence Models
Deeply Embedded Knowledge Representation & Reasoning For Natural Language Question Answering: A Practitioner's Perspective
Generating Synthetic Data for Task-Oriented Semantic Parsing with Hierarchical Representations
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Log-Linear Reformulation of the Noisy Channel Model for Document-Level Neural Machine Translation
On the Discrepancy between Density Estimation and Sequence Generation
Reading the Manual: Event Extraction as Definition Comprehension