NLP researcher at Northeastern University working on sign language translation and human-AI collaboration evaluation
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
5
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-16) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: the record lacks the per-work venue, type and authorship detail this axis needs. Once complete, it would measure publication volume and productivity shape across the year-by-year works from 2019 through 2026.
Impact—
Not yet scored: citation-level impact data is unavailable beyond the recorded h-index of 5 and i10-index of 3. This axis would measure citations, yearly citation pace and influence on follow-up work once the citation record is complete.
Focus0/100
Scores 0, meaning maximal dispersion rather than absence of direction: the field split is exactly 50/50 between computational linguistics / sign language NLP and human-AI collaboration evaluation, and the five topic labels (NLP techniques 26, speech and dialogue 20, hearing impairment and communication 19, gesture recognition 18, multimodal ML 12) are weighted fairly evenly.
Collaboration44/100
Scores 44, a lower-middle position. The OpenAlex record lists 8 distinct recent coauthors, and both Evolve-reviewed 2026 papers place İnan as a middle author rather than corresponding author. The recurring set spans Vasileios Baltatzis, Connor Gillis, Raja Kushalnagar, Lorna Quandt, Leah Findlater, Colin Lea, Saki Imai and Malihe Alikhani, consistent with team-based work across the record's two fields.
Activity100/100
Scores 100, the strongest axis in the record. Year-by-year works climb from 1 in 2019 and 2 in 2021 to 8 (2022), 6 (2023), 7 (2024), a peak of 16 in 2025 and 8 already in 2026, with 31 works in the most recent three-year window — a steep, sustained productivity ramp.
Reproducibility55/100
Scores 55, computed from 2 reproducibility-assessed papers with a mean readiness of 55. Both Evolve-reviewed papers rate medium: DiscoSign's SCA/CGC gains rely on metrics that are partly self-enforced and judged by the same LLM, while the productive-success framework rests on correlational evidence across 4 tasks with judge-bias caveats.
Research summary
Mert İnan (Northeastern University, US; ORCID 0000-0001-6972-411X) works across two roughly equal lines of research: computational linguistics for sign language and evaluation of human-AI collaboration — the OpenAlex field split is exactly 50/50. The 2026 arXiv paper DiscoSign introduces the first discourse-aware text-to-ASL-gloss translation framework, with new metrics for discourse coherence, spatial coreference and question-answer clauses; Evolve notes large SCA/CGC gains while flagging metrics that are partly self-enforced and judged by the same LLM. A second 2026 paper, From Task Success to Productive Success, proposes scoring collaboration as Pz = z(Q) − z(C), trading quality against interaction cost, supported by correlational evidence across four tasks with robustness checks and judge-bias caveats. Bibliometrics describe a young but fast-moving record: h-index 5, i10-index 3, yearly works rising from 1 in 2019 to a peak of 16 in 2025 with 8 already in 2026, and 31 works in the last three years. Topics concentrate on NLP techniques (26), speech and dialogue systems (20), hearing impairment and communication (19), hand gesture recognition (18) and multimodal ML (12). The pace drives an activity score of 100; a focus score of 0 reflects the deliberately broad two-field spread, and reproducibility scores 55 across two assessed papers, both rated medium.
Collaboration pattern
Collaboration score 44 reflects a modest, team-oriented pattern: the OpenAlex record lists 8 distinct recent coauthors, and both Evolve-reviewed 2026 papers place İnan as a middle author rather than corresponding author. The recurring collaborator set includes Vasileios Baltatzis, Connor Gillis, Raja Kushalnagar, Lorna Quandt, Leah Findlater, Colin Lea, Saki Imai and Malihe Alikhani — consistent with the record's 50/50 split between sign-language NLP and human-AI collaboration evaluation.
Research keywords
Highlights
DiscoSign: first discourse-aware text-to-ASL-gloss translation
Scoring human-AI collaboration as Pz = z(Q) − z(C)
Timeline
- 2019First year with recorded works in the OpenAlex record (1 work), marking the start of the visible publication trail.
- 2022Recorded works jump to 8, up from 2 in 2021 — the first clear acceleration in output.
- 2025Peak activity year: 16 recorded works, bringing the recent three-year total to 31.
- 2026Two arXiv papers enter the Evolve catalog — DiscoSign and the productive-success evaluation framework — with 8 works already recorded this year.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometrics come from the OpenAlex record only; citation-impact data beyond h-index 5 and i10-index 3 is not available, so the impact axis is unscored.
- Both Evolve-reviewed papers are 2026 arXiv preprints; peer-review status is not reflected in the catalog.
- Profile is name-resolved from public bibliographic data tied to ORCID 0000-0001-6972-411X; no biographical information beyond affiliation was used.
- 2026 work counts cover a partial year and may rise; output-axis scoring remains unavailable in this snapshot.