DeepLo @ ACL 2018

5 papers

Top Research Directions

The 20 research directions with DeepLo @ ACL 2018 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Aligning Global Semantics with Local Spatial Precision120.0%
2Automating Lexical Semantic Resource Construction120.0%
3Breaking the Triplet Bottleneck in Multimodal Translation120.0%
4Contextual Morphological Disambiguation120.0%
5Downstream Task Transferability of Text Representations120.0%
6High Information Density Curation for Model Training120.0%
7Integrating External Semantic Priors into Topic Models120.0%
8Learning with Instance Dependent Label Noise120.0%
9Machine Translation Without Massive Parallel Corpora120.0%
10Multi-Task Learning for Data-Scarce Domains120.0%
11Noise Transition Matrix Estimation for Noisy Labels120.0%
12Resolving Lexical Ambiguity with Multimodal Machine Translation120.0%
13Semantic Feature Extraction from Pretrained Convolutional Networks120.0%
14Specializing Word Embeddings for Technical Domains120.0%
15Synthetic Target Generation for Multimodal Translation120.0%
16The Geometry of Embedding Anisotropy120.0%
17The Semantic Gap in Domain Specific Embeddings120.0%
18Visual Grounding for Semantic Disambiguation120.0%
19Visual State Initialization for Multimodal Sequence Generation120.0%
20Why Neural Networks Misrepresent Low Frequency Words120.0%

Download all directions as CSV

Institutions

Institutions credited by DeepLo @ ACL 2018 papers: a paper credits every institution named in its affiliations, once. 7 institutions share 5 credited papers.

#InstitutionPapersShare
1University of Copenhagen 240.0%
2ADAPT - Centre for Digital Content Technology 120.0%
3Dublin City University 120.0%
4IT University of Copenhagen 120.0%
5New York University 120.0%
6Saarland University 120.0%
7University of Wisconsin–Madison 120.0%

Download all institutions as CSV

About this data

Papers. DeepLo @ ACL 2018 lists 5 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.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.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 5 of 5 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 2026-11-20 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “DeepLo @ ACL 2018”, https://lacuna.tiptreesystems.com/venue/deeplo-acl/2018.

Top Authors

AuthorPapers
Anders Søgaard2
Barbara Plank1
Dietrich Klakow1
Isabelle Augenstein1
Johannes Bjerva1
Marcel Bollmann1
Michael A. Hedderich1
Prathusha K. Sarma1
Qun Liu1
William A. Sethares1
Yingyu Liang1

Impactful Papers

Papers from DeepLo @ ACL 2018 that shaped research clusters.

Foundational

Influential

Papers

Title
Character-level Supervision for Low-resource POS Tagging
Domain Adapted Word Embeddings for Improved Sentiment Classification
Multimodal Neural Machine Translation for Low-resource Language Pairs using Synthetic Data
Multi-task learning for historical text normalization: Size matters
Training a Neural Network in a Low-Resource Setting on Automatically Annotated Noisy Data